PO.ID.Exact

Exact (point) identification: back-door and front-door adjustment, IV/LATE, regression discontinuity, proximal inference, dynamic regimes, and related theorems.

DTR 26 core · 30 supporting · 5 submodules Identification for dynamic treatment regimes: sequential exchangeability and the g-formula. Dynamic­LATE 60 core · 43 supporting · 4 submodules Dynamic LATE: identification of complier effects in multi-period instrumented settings. Heckman­Roy 24 core · 17 supporting · 2 submodules The Heckman/Roy selection model: identification of treatment parameters under self-selection. Multiple­Instrument­IV 80 core · 42 supporting · 5 submodules Multiple-instrument IV: Mogstad-Torgovitsky-Walters finite-support 2SLS response-type algebra and sign-alignment results. Partial­Linear 17 core · 19 supporting · 2 submodules Partially linear continuous-treatment identification: the potential-outcome setup, homogeneous dose-response restriction, Robinson residualization, and slope-identification theorem. Proximal 22 core · 37 supporting · 4 submodules Proximal causal inference: identification through outcome- and treatment-confounding proxies via bridge functions. QTE 9 core · 8 supporting · 2 submodules Quantile treatment effects (Firpo 2007): backdoor identification of the marginal QTE at level τ — the τ-quantile of the treated potential outcome Y(1) minus that of the control Y(0). DistributionalBackdoor lifts the mean-level backdoor to the whole potential-outcome law via inverse-probability weighting; QuantileEffect adds the quantile layer, identifying the QTE as the difference of the identified laws quantiles. RDD 31 core · 32 supporting · 3 submodules Regression discontinuity: identification of the cutoff effect from continuity of conditional regressions. Variable­Intensity­IV 49 core · 26 supporting · 2 submodules Variable-intensity instrumental variables: Angrist-Imbens average causal response over ordered treatment margins.
ATE 25 core · 36 supporting This file proves backdoor identification for the average treatment effect in the potential-outcome framework. ★ POBackdoorSystem★ cate_backdoor★ ate_backdoor★ regression_adjustment

Backdoor Average Treatment Effect

This file proves backdoor identification for the average treatment effect in the potential-outcome framework. It connects conditional independence, consistency, and overlap assumptions to the standard adjustment formula for binary treatment and real-valued outcomes.

The adjustment covariate has an arbitrary measurable value space, so the same setup covers discrete, continuous, and vector-valued covariates. The proof uses conditional expectations with respect to the sigma-algebra generated by the covariate.

The main public results are cate_backdoor_of_propScore_ne, which isolates the per-arm propensity nonvanishing condition, cate_backdoor and ate_backdoor, which discharge it from two-sided overlap, and regression_adjustment, which shows the adjusted conditional functional is the observable regression E[Y | D=d, X].

structure POBackdoorSystem reviewed
Causalean.PO

A backdoor system consists of a binary treatment variable, a real-valued outcome variable, and an adjustment covariate with an arbitrary measurable value space, where the three variables are pairwise distinct.

Definition (Lean source)
P :
γ :
D :
P.V
Y :
P.V
Xvar :
POVar P γ
hDbool :
P.X D ≃ᵐ Bool
hYreal :
P.X Y ≃ᵐ ℝ
hDY :
D ≠ Y
hDX :
D ≠ Xvar.v
hYX :
Y ≠ Xvar.v
Causalean.PO.POBackdoorSystem · Causalean/PO/ID/Exact/ATE.lean:54 · uses POSystem
def dVar reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the treatment potential-outcome variable is the system's treatment represented with the two treatment arms.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
dVar S :
⟨S.D, S.hDbool⟩
Causalean.PO.POBackdoorSystem.dVar · Causalean/PO/ID/Exact/ATE.lean:75 · uses POBackdoorSystem , POSystem , POVar
def yVar reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the outcome potential-outcome variable is the system's real-valued outcome.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
yVar S :
POVar P ℝ
⟨S.Y, S.hYreal⟩
Causalean.PO.POBackdoorSystem.yVar · Causalean/PO/ID/Exact/ATE.lean:77 · uses POBackdoorSystem , POSystem , POVar
def xVar reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the adjustment-covariate potential-outcome variable is its specified covariate.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
xVar S :
POVar P γ
S.Xvar
Causalean.PO.POBackdoorSystem.xVar · Causalean/PO/ID/Exact/ATE.lean:79 · uses POBackdoorSystem , POSystem , POVar
def YofD reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system and a treatment arm, the potential outcome under that arm assigns every unit its real-valued outcome if treatment were set to that arm.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
d :
YofD S d :
P.Ω → ℝ
S.yVar.cfUnder S.dVar d
Causalean.PO.POBackdoorSystem.YofD · Causalean/PO/ID/Exact/ATE.lean:82 · uses POBackdoorSystem , POSystem
def factualD reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the factual treatment assigns every unit its observed treatment arm.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
factualD S :
P.Ω → Bool
S.dVar.factual
Causalean.PO.POBackdoorSystem.factualD · Causalean/PO/ID/Exact/ATE.lean:84 · uses POBackdoorSystem , POSystem
def factualY reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the factual outcome assigns every unit its observed real-valued outcome.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
factualY S :
P.Ω → ℝ
S.yVar.factual
Causalean.PO.POBackdoorSystem.factualY · Causalean/PO/ID/Exact/ATE.lean:86 · uses POBackdoorSystem , POSystem
def factualX reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the factual covariate assigns every unit its observed adjustment-covariate value.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
factualX S :
P.Ω → γ
S.xVar.factual
Causalean.PO.POBackdoorSystem.factualX · Causalean/PO/ID/Exact/ATE.lean:88 · uses POBackdoorSystem , POSystem
def sigmaX reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the covariate σ-algebra is the σ-algebra on the sample space generated by the factual covariate.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
sigmaX S :
comap S.factualX inferInstance
Causalean.PO.POBackdoorSystem.sigmaX · Causalean/PO/ID/Exact/ATE.lean:105 · uses POBackdoorSystem , POSystem
def yUnderD reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system and a treatment arm, the regimed outcome variable is the outcome variable under the regime fixing treatment to that arm.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
d :
yUnderD S d :
⟨S.yVar, Regime.single S.D (S.hDbool.symm d)⟩
def cfBundle reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the counterfactual bundle contains the treated and untreated potential outcomes for unconfoundedness.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
cfBundle S :
POCFBundle.cons (S.yUnderD true) <| POCFBundle.cons (S.yUnderD false) <| POCFBundle.nil P
Causalean.PO.POBackdoorSystem.cfBundle · Causalean/PO/ID/Exact/ATE.lean:123 · uses POBackdoorSystem , POCFBundle , POSystem
def propScore reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system and a treatment arm, the propensity score assigns each unit the conditional probability of receiving that arm given the covariate σ-algebra.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
d :
propScore S d :
P.Ω → ℝ
P.μ[S.dVar.indicator d | S.sigmaX]
Causalean.PO.POBackdoorSystem.propScore · Causalean/PO/ID/Exact/ATE.lean:130 · uses POBackdoorSystem , POSystem
def CATE reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system and a treatment arm, the conditional mean potential outcome assigns each unit the conditional mean of that arm's potential outcome given the covariate.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
d :
CATE S d :
P.Ω → ℝ
P.μ[S.YofD d | S.sigmaX]
Causalean.PO.POBackdoorSystem.CATE · Causalean/PO/ID/Exact/ATE.lean:134 · uses POBackdoorSystem , POSystem
def ATE reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the average treatment effect is the population mean of the treated potential outcome minus the untreated potential outcome.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
ATE S :
∫ ω, S.YofD true ω - S.YofD false ω ∂P.μ
Causalean.PO.POBackdoorSystem.ATE · Causalean/PO/ID/Exact/ATE.lean:198 · uses POBackdoorSystem , POSystem
def adjustedCE reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system and a treatment arm, the adjusted conditional functional is the covariate-conditional mean of factual outcome times the indicator for that arm, divided by that arm's propensity score.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
d :
adjustedCE S d :
P.Ω → ℝ
fun ω
=> P.μ[fun ω' => S.factualY ω' * S.dVar.indicator d ω' | S.sigmaX] ω / S.propScore d ω
Causalean.PO.POBackdoorSystem.adjustedCE · Causalean/PO/ID/Exact/ATE.lean:201 · uses POBackdoorSystem , POSystem
def adjustedATE reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the adjusted average treatment effect is the population mean of the adjusted conditional functional for treatment minus that for control.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
adjustedATE S :
∫ ω, S.adjustedCE true ω - S.adjustedCE false ω ∂P.μ
Causalean.PO.POBackdoorSystem.adjustedATE · Causalean/PO/ID/Exact/ATE.lean:219 · uses POBackdoorSystem , POSystem
structure Assumptions reviewed
Causalean.PO.POBackdoorSystem

The backdoor (Rosenbaum–Rubin / Firpo) identifying assumptions for the ATE, at the potential-outcome level, for binary treatment D and real outcome Y adjusted for covariates X: the observed outcome equals the potential outcome of the realized treatment arm, treatment is conditionally independent of the treated and untreated potential outcomes given the covariates, every covariate stratum has a positive chance of either treatment arm, and the treated and untreated potential outcomes are integrable.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
consistency :
P.Consistency

Consistency (SUTVA): the observed outcome equals the potential outcome of the realized arm — on {D = d}, Y = Y(d). Links observed data to the potential outcomes.

unconfoundedness :
P.CondIndepCF (RegimedVar.ofFactual S.dVar) S.cfBundle (RegimedVar.ofFactual S.xVar) P.μ

Unconfoundedness (conditional ignorability): treatment is independent of the potential outcomes given the covariates, D ⟂ (Y(1), Y(0)) | X. Stated as conditional independence of the realized D and the counterfactual bundle (Y(1), Y(0)) given σ(X).

overlap :
∀ᵐ ω ∂P.μ, 0 < S.propScore true ω ∧ S.propScore true ω < 1

Overlap (common support): every covariate stratum has a positive chance of EITHER arm — 0 < P[D=1 | σ(X)] < 1 a.s. Two-sided here because the ATE needs both arms identified at every x. Bare positivity (not a uniform c ≤ e ≤ 1−c strong-overlap bound, which is only needed for efficient-estimator asymptotics), mirroring DTR.

integrable_Y1 :
Integrable (S.YofD true) P.μ

Regularity: the treated potential outcome Y(1) is integrable (so E[Y(1)] is well-defined).

integrable_Y0 :
Integrable (S.YofD false) P.μ

Regularity: the control potential outcome Y(0) is integrable (so E[Y(0)] is well-defined).

Causalean.PO.POBackdoorSystem.Assumptions · Causalean/PO/ID/Exact/ATE.lean:226 · uses POBackdoorSystem , POSystem
theorem cate_backdoor reviewed
Causalean.PO.POBackdoorSystem

CATE-level backdoor identification. Under the backdoor identification assumptions — consistency, unconfoundedness, and two-sided overlap of the propensity score, together with integrability of the potential outcomes, for a treatment arm d, the conditional average treatment effect given the covariates equals the adjusted-outcome functional:

Formal statement
P :
shared
γ :
Type u_1
shared
S :
shared
hA :
S.Assumptions
d :
S.CATE d =ᵐ[P.μ] S.adjustedCE d
Proof (Lean source)
theorem cate_backdoor [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.Assumptions) (d : Bool) : S.CATE d =ᵐ[P.μ] S.adjustedCE d := S.cate_backdoor_of_propScore_ne hA.consistency hA.unconfoundedness hA.integrable_Y1 hA.integrable_Y0 d (S.propScore_ne_of_overlap hA.overlap d)
theorem ate_backdoor reviewed
Causalean.PO.POBackdoorSystem

Integrated backdoor ATE identification. Under the backdoor identification assumptions — consistency, unconfoundedness, two-sided overlap, and integrable potential outcomes, the average treatment effect equals the adjusted-outcome functional obtained by averaging the CATE-level backdoor identity over the covariate distribution.

Formal statement
P :
shared
γ :
Type u_1
shared
S :
shared
hA :
S.Assumptions
S.ATE = S.adjustedATE
Proof (Lean source)
theorem ate_backdoor [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.Assumptions) : S.ATE = S.adjustedATE := by unfold POBackdoorSystem.ATE POBackdoorSystem.adjustedATE -- `CATE d = xVar.condExpGiven (YofD d) P.μ` definitionally. have hf' : S.xVar.condExpGiven (S.YofD true) P.μ =ᵐ[P.μ] S.adjustedCE true := S.cate_backdoor hA true have hg' : S.xVar.condExpGiven (S.YofD false) P.μ =ᵐ[P.μ] S.adjustedCE false := S.cate_backdoor hA false exact S.xVar.integral_sub_eq_integral_sub_of_condExpGiven_ae_eq hA.integrable_Y1 hA.integrable_Y0 hf' hg'
def factualDX reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the factual treatment--covariate pair assigns each unit its observed treatment arm and covariate value.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
factualDX S :
P.Ω → Bool × γ
fun ω => (S.factualD ω, S.factualX ω)
Causalean.PO.POBackdoorSystem.factualDX · Causalean/PO/ID/Exact/ATE.lean:549 · uses POBackdoorSystem , POSystem
def sigmaDX reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the joint treatment--covariate σ-algebra is the σ-algebra on the sample space generated by the factual treatment--covariate pair.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
sigmaDX S :
comap S.factualDX inferInstance
Causalean.PO.POBackdoorSystem.sigmaDX · Causalean/PO/ID/Exact/ATE.lean:561 · uses POBackdoorSystem , POSystem
def outcomeReg reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the outcome regression assigns each unit the conditional mean of the factual outcome given its factual treatment and covariate.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
outcomeReg S :
P.Ω → ℝ
P.μ[S.factualY | S.sigmaDX]
Causalean.PO.POBackdoorSystem.outcomeReg · Causalean/PO/ID/Exact/ATE.lean:597 · uses POBackdoorSystem , POSystem
def regFn reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the value-space outcome regression maps a treatment--covariate value to the corresponding conditional mean factual outcome.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
regFn S :
Bool × γ → ℝ
S.exists_regFn.choose
Causalean.PO.POBackdoorSystem.regFn · Causalean/PO/ID/Exact/ATE.lean:632 · uses POBackdoorSystem , POSystem
def eLift reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the value-space propensity representative maps each covariate value to the treated-arm propensity score at that value.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
eLift S :
γ → ℝ
S.exists_propScoreLift.choose
Causalean.PO.POBackdoorSystem.eLift · Causalean/PO/ID/Exact/ATE.lean:655 · uses POBackdoorSystem , POSystem
theorem regression_adjustment reviewed
Causalean.PO.POBackdoorSystem

Regression-adjustment identification (observable). For a treatment arm d, if the observed outcome is integrable and the covariate- conditional probability of receiving arm d is almost surely nonzero, then the backdoor adjustment functional for arm d equals the value-space outcome regression evaluated at the arm d:

Formal statement
P :
shared
γ :
Type u_1
shared
S :
shared
d :
hY :
Integrable S.factualY P.μ
h_ne :
∀ᵐ ω ∂P.μ, S.propScore d ω ≠ 0
S.adjustedCE d =ᵐ[P.μ] (fun ω => S.regFn (d, S.factualX ω))
Proof (Lean source)
theorem regression_adjustment [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (d : Bool) (hY : Integrable S.factualY P.μ) (h_ne : ∀ᵐ ω ∂P.μ, S.propScore d ω ≠ 0) : S.adjustedCE d =ᵐ[P.μ] (fun ω => S.regFn (d, S.factualX ω)) := by have hratio_def : S.adjustedCE d = S.xVar.condExpRatio (fun ω => S.factualY ω * S.dVar.indicator d ω) (S.dVar.indicator d) P.μ := by funext ω unfold POBackdoorSystem.adjustedCE POBackdoorSystem.propScore POBackdoorSystem.sigmaX POBackdoorSystem.factualX POVar.condExpRatio POVar.condExpGiven rfl rw [hratio_def] refine S.xVar.condExpRatio_eq_of_mul (g := fun ω => S.factualY ω * S.dVar.indicator d ω) (h := S.dVar.indicator d) (target := fun ω => S.regFn (d, S.factualX ω)) ?_ ?_ · have hYint : Integrable S.factualY P.μ := hY · let s : Set P.Ω := S.dVar.event d let target : P.Ω → ℝ := fun ω => S.regFn (d, S.factualX ω) have hsDX : MeasurableSet[S.sigmaDX] s := by change MeasurableSet[comap S.factualDX inferInstance] (S.factualD ⁻¹' {d}) exact ⟨Prod.fst ⁻¹' {d}, measurableSet_singleton d |>.preimage measurable_fst, rfl⟩ have hs : MeasurableSet s := S.dVar.measurableSet_event d (measurableSet_singleton d) have hmul_indicator : (fun ω => S.factualY ω * S.dVar.indicator d ω) = s.indicator S.factualY := by funext ω by_cases hω : ω ∈ s · have hind : S.dVar.indicator d ω = 1 := S.dVar.indicator_apply_eq_one hω rw [hind, mul_one, Set.indicator_of_mem hω] · have hD : S.factualD ω ≠ d := hω have hind : S.dVar.indicator d ω = 0 := S.dVar.indicator_apply_eq_zero hD rw [hind, mul_zero, Set.indicator_of_notMem hω] have htarget_meas : Measurable[S.sigmaX] target := by fun_prop have htarget_sm : StronglyMeasurable[S.sigmaX] target := by fun_prop have houtcome_target : s.indicator S.outcomeReg = s.indicator target := by funext ω by_cases hω : ω ∈ s · have hD : S.factualD ω = d := hω rw [Set.indicator_of_mem hω, Set.indicator_of_mem hω] rw [congrFun S.outcomeReg_eq_regFn ω] simp [target, POBackdoorSystem.factualDX, hD] · rw [Set.indicator_of_notMem hω, Set.indicator_of_notMem hω] have htower : P.μ[s.indicator S.factualY | S.sigmaX] =ᵐ[P.μ] P.μ[s.indicator S.outcomeReg | S.sigmaX] := by simpa [s, POBackdoorSystem.outcomeReg] using condExp_setIndicator_condExp_of_le (μ := P.μ) (m := S.sigmaX) (m' := S.sigmaDX) S.sigmaX_le_sigmaDX S.sigmaDX_le hsDX hYint have hleft : P.μ[fun ω => S.factualY ω * S.dVar.indicator d ω | S.sigmaX] =ᵐ[P.μ] P.μ[s.indicator target | S.sigmaX] := (MeasureTheory.condExp_congr_ae (m := S.sigmaX) (μ := P.μ) (Filter.EventuallyEq.of_eq hmul_indicator)).trans (htower.trans (MeasureTheory.condExp_congr_ae (m := S.sigmaX) (μ := P.μ) (Filter.EventuallyEq.of_eq houtcome_target))) have hind_int : Integrable (S.dVar.indicator d) P.μ := by fun_prop have htarget_mul_indicator : target * S.dVar.indicator d = s.indicator target := by funext ω by_cases hω : ω ∈ s · have hind : S.dVar.indicator d ω = 1 := S.dVar.indicator_apply_eq_one hω rw [Pi.mul_apply, hind, mul_one, Set.indicator_of_mem hω] · have hD : S.factualD ω ≠ d := hω have hind : S.dVar.indicator d ω = 0 := S.dVar.indicator_apply_eq_zero hD rw [Pi.mul_apply, hind, mul_zero, Set.indicator_of_notMem hω] have htarget_mul_int : Integrable (target * S.dVar.indicator d) P.μ := by rw [htarget_mul_indicator] have houtcome_target' : s.indicator (P.μ[S.factualY | S.sigmaDX]) = s.indicator target := by simpa [POBackdoorSystem.outcomeReg] using houtcome_target exact MeasureTheory.Integrable.indicator (MeasureTheory.integrable_condExp (μ := P.μ) (m := S.sigmaDX) (f := S.factualY)) hs |>.congr (Filter.EventuallyEq.of_eq houtcome_target') have hpull : P.μ[target * S.dVar.indicator d | S.sigmaX] =ᵐ[P.μ] target * P.μ[S.dVar.indicator d | S.sigmaX] := MeasureTheory.condExp_mul_of_stronglyMeasurable_left (m := S.sigmaX) (μ := P.μ) htarget_sm htarget_mul_int hind_int change P.μ[fun ω => S.factualY ω * S.dVar.indicator d ω | S.sigmaX] =ᵐ[P.μ] P.μ[S.dVar.indicator d | S.sigmaX] * target refine hleft.trans ?_ refine (MeasureTheory.condExp_congr_ae (m := S.sigmaX) (μ := P.μ) (Filter.EventuallyEq.of_eq htarget_mul_indicator.symm)).trans ?_ exact hpull.trans (Filter.EventuallyEq.of_eq (by funext ω exact mul_comm _ _)) · have hEq : S.xVar.condExpGiven (S.dVar.indicator d) P.μ = S.propScore d := by unfold POVar.condExpGiven POBackdoorSystem.propScore POBackdoorSystem.sigmaX POBackdoorSystem.factualX rfl rw [hEq] exact h_ne
36 supporting declarations (lemmas, instances)
  • measurable_YofD lemma — Potential outcomes under fixed treatment arms are measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    Measurable (S.YofD d)
    Proof (Lean source)
    @[fun_prop] lemma measurable_YofD (d : Bool) : Measurable (S.YofD d) := S.yVar.measurable_cfUnder S.dVar d
    Causalean.PO.POBackdoorSystem.measurable_YofD · Causalean/PO/ID/Exact/ATE.lean:91
  • measurable_factualD lemma — The observed treatment is measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualD
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualD : Measurable S.factualD := S.dVar.measurable_factual
    Causalean.PO.POBackdoorSystem.measurable_factualD · Causalean/PO/ID/Exact/ATE.lean:95
  • measurable_factualY lemma — The observed outcome is measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualY
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualY : Measurable S.factualY := S.yVar.measurable_factual
    Causalean.PO.POBackdoorSystem.measurable_factualY · Causalean/PO/ID/Exact/ATE.lean:98
  • measurable_factualX lemma — The observed covariate is measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualX
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualX : Measurable S.factualX := S.xVar.measurable_factual
    Causalean.PO.POBackdoorSystem.measurable_factualX · Causalean/PO/ID/Exact/ATE.lean:101
  • sigmaX_le lemma — The covariate sigma-algebra is a sub-sigma-algebra of the ambient one.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    S.sigmaX ≤ (inferInstance : MeasurableSpace P.Ω)
    Proof (Lean source)
    lemma sigmaX_le : S.sigmaX ≤ (inferInstance : MeasurableSpace P.Ω) := S.measurable_factualX.comap_le
    Causalean.PO.POBackdoorSystem.sigmaX_le · Causalean/PO/ID/Exact/ATE.lean:109
  • measurable_factualX_sigmaX lemma — The observed covariate is measurable for the covariate sigma-algebra it generates.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable[S.sigmaX] S.factualX
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualX_sigmaX : Measurable[S.sigmaX] S.factualX := comap_measurable S.factualX
    Causalean.PO.POBackdoorSystem.measurable_factualX_sigmaX · Causalean/PO/ID/Exact/ATE.lean:113
  • propScore_eq lemma — The propensity score at a treatment arm is the conditional expectation of that arm's treatment indicator given the covariate σ-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    S.propScore d = P.μ[S.dVar.indicator d | S.sigmaX]
    Proof (Lean source)
    @[causal_defs_simps] lemma propScore_eq (d : Bool) : S.propScore d = P.μ[S.dVar.indicator d | S.sigmaX] := rfl
    Causalean.PO.POBackdoorSystem.propScore_eq · Causalean/PO/ID/Exact/ATE.lean:141
  • CATE_eq lemma — The conditional mean potential outcome at a treatment arm is the conditional expectation of that arm's potential outcome given the covariate σ-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    S.CATE d = P.μ[S.YofD d | S.sigmaX]
    Proof (Lean source)
    @[causal_defs_simps] lemma CATE_eq (d : Bool) : S.CATE d = P.μ[S.YofD d | S.sigmaX] := rfl
    Causalean.PO.POBackdoorSystem.CATE_eq · Causalean/PO/ID/Exact/ATE.lean:148
  • stronglyMeasurable_propScore_sigmaX lemma — The propensity score is strongly measurable for the covariate sigma-algebra: it is a conditional expectation given that sigma-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    StronglyMeasurable[S.sigmaX] (S.propScore d)
    Proof (Lean source)
    @[fun_prop] lemma stronglyMeasurable_propScore_sigmaX (d : Bool) : StronglyMeasurable[S.sigmaX] (S.propScore d) := MeasureTheory.stronglyMeasurable_condExp
    Causalean.PO.POBackdoorSystem.stronglyMeasurable_propScore_sigmaX · Causalean/PO/ID/Exact/ATE.lean:155
  • measurable_propScore_sigmaX lemma — The propensity score is measurable for the covariate sigma-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    Measurable[S.sigmaX] (S.propScore d)
    Proof (Lean source)
    @[fun_prop] lemma measurable_propScore_sigmaX (d : Bool) : Measurable[S.sigmaX] (S.propScore d) := (MeasureTheory.stronglyMeasurable_condExp).measurable
    Causalean.PO.POBackdoorSystem.measurable_propScore_sigmaX · Causalean/PO/ID/Exact/ATE.lean:162
  • measurable_propScore lemma — The propensity score is measurable for the ambient sigma-algebra on the sample space.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    Measurable (S.propScore d)
    Proof (Lean source)
    @[fun_prop] lemma measurable_propScore (d : Bool) : Measurable (S.propScore d) := (S.measurable_propScore_sigmaX d).mono S.sigmaX_le le_rfl
    Causalean.PO.POBackdoorSystem.measurable_propScore · Causalean/PO/ID/Exact/ATE.lean:167
  • integrable_propScore lemma — The propensity score is integrable: it is a conditional expectation.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    Integrable (S.propScore d) P.μ
    Proof (Lean source)
    @[fun_prop] lemma integrable_propScore (d : Bool) : Integrable (S.propScore d) P.μ := MeasureTheory.integrable_condExp
    Causalean.PO.POBackdoorSystem.integrable_propScore · Causalean/PO/ID/Exact/ATE.lean:173
  • stronglyMeasurable_CATE_sigmaX lemma — The conditional mean potential outcome is strongly measurable for the covariate sigma-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    StronglyMeasurable[S.sigmaX] (S.CATE d)
    Proof (Lean source)
    @[fun_prop] lemma stronglyMeasurable_CATE_sigmaX (d : Bool) : StronglyMeasurable[S.sigmaX] (S.CATE d) := MeasureTheory.stronglyMeasurable_condExp
    Causalean.PO.POBackdoorSystem.stronglyMeasurable_CATE_sigmaX · Causalean/PO/ID/Exact/ATE.lean:178
  • measurable_CATE lemma — The conditional mean potential outcome is measurable for the ambient sigma-algebra on the sample space.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    Measurable (S.CATE d)
    Proof (Lean source)
    @[fun_prop] lemma measurable_CATE (d : Bool) : Measurable (S.CATE d) := ((MeasureTheory.stronglyMeasurable_condExp (μ := P.μ) (m := S.sigmaX) (f := S.YofD d)).measurable).mono S.sigmaX_le le_rfl
    Causalean.PO.POBackdoorSystem.measurable_CATE · Causalean/PO/ID/Exact/ATE.lean:185
  • integrable_CATE lemma — The conditional mean potential outcome is integrable: it is a conditional expectation.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    Integrable (S.CATE d) P.μ
    Proof (Lean source)
    @[fun_prop] lemma integrable_CATE (d : Bool) : Integrable (S.CATE d) P.μ := MeasureTheory.integrable_condExp
    Causalean.PO.POBackdoorSystem.integrable_CATE · Causalean/PO/ID/Exact/ATE.lean:192
  • adjustedCE_def lemma — The adjusted conditional functional at a treatment arm sends a unit to the conditional expectation, given the covariate σ-algebra, of the factual outcome times that arm's treatment indicator, divided by the propensity score of that arm.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    d :
    S.adjustedCE d
    = fun ω => P.μ[fun ω' => S.factualY ω' * S.dVar.indicator d ω' | S.sigmaX] ω / S.propScore d ω
    Proof (Lean source)
    @[causal_defs_simps] lemma adjustedCE_def (d : Bool) : S.adjustedCE d = fun ω => P.μ[fun ω' => S.factualY ω' * S.dVar.indicator d ω' | S.sigmaX] ω / S.propScore d ω := rfl
    Causalean.PO.POBackdoorSystem.adjustedCE_def · Causalean/PO/ID/Exact/ATE.lean:208
  • integrable_YofD lemma — Under the backdoor assumption bundle the potential outcome of either treatment arm is integrable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    hA :
    S.Assumptions
    d :
    Integrable (S.YofD d) P.μ
    Proof (Lean source)
    @[fun_prop] lemma Assumptions.integrable_YofD [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.Assumptions) (d : Bool) : Integrable (S.YofD d) P.μ := by cases d · exact hA.integrable_Y0 · exact hA.integrable_Y1
    Causalean.PO.POBackdoorSystem.Assumptions.integrable_YofD · Causalean/PO/ID/Exact/ATE.lean:262
  • integrable_factualY_of_consistency lemma — Factual Y is integrable whenever both treatment-arm potential outcomes are integrable and consistency links the observed outcome to the realized arm.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    hcons :
    P.Consistency
    hY1 :
    Integrable (S.YofD true) P.μ
    hY0 :
    Integrable (S.YofD false) P.μ
    Integrable S.factualY P.μ
    Proof (Lean source)
    lemma integrable_factualY_of_consistency (hcons : P.Consistency) (hY1 : Integrable (S.YofD true) P.μ) (hY0 : Integrable (S.YofD false) P.μ) : Integrable S.factualY P.μ := by have hY1_ind : Integrable (fun ω => S.YofD true ω * S.dVar.indicator true ω) P.μ := by fun_prop have hY0_ind : Integrable (fun ω => S.YofD false ω * S.dVar.indicator false ω) P.μ := by fun_prop have hsum_int : Integrable (fun ω => S.YofD true ω * S.dVar.indicator true ω + S.YofD false ω * S.dVar.indicator false ω) P.μ := by fun_prop refine hsum_int.congr ?_ filter_upwards with ω have htrue := congr_fun (POVar.factual_mul_indicator_eq_cfUnder_mul_indicator_fn hcons S.yVar S.dVar true (Ne.symm S.hDY)) ω have hfalse := congr_fun (POVar.factual_mul_indicator_eq_cfUnder_mul_indicator_fn hcons S.yVar S.dVar false (Ne.symm S.hDY)) ω have htrue' : S.YofD true ω * S.dVar.indicator true ω = S.factualY ω * S.dVar.indicator true ω := by simpa [POBackdoorSystem.YofD, POBackdoorSystem.factualY] using htrue.symm have hfalse' : S.YofD false ω * S.dVar.indicator false ω = S.factualY ω * S.dVar.indicator false ω := by simpa [POBackdoorSystem.YofD, POBackdoorSystem.factualY] using hfalse.symm have hsum := S.dVar.indicator_add_indicator_not ω calc S.YofD true ω * S.dVar.indicator true ω + S.YofD false ω * S.dVar.indicator false ω = S.factualY ω * S.dVar.indicator true ω + S.factualY ω * S.dVar.indicator false ω := by rw [htrue', hfalse'] _ = S.factualY ω * (S.dVar.indicator true ω + S.dVar.indicator false ω) := by ring _ = S.factualY ω := by rw [hsum, mul_one]
    Causalean.PO.POBackdoorSystem.integrable_factualY_of_consistency · Causalean/PO/ID/Exact/ATE.lean:271
  • integrable_factualY lemma — The observed outcome is integrable under the backdoor assumption bundle.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    hA :
    S.Assumptions
    Integrable S.factualY P.μ
    Proof (Lean source)
    @[fun_prop] lemma Assumptions.integrable_factualY [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.Assumptions) : Integrable S.factualY P.μ := S.integrable_factualY_of_consistency hA.consistency hA.integrable_Y1 hA.integrable_Y0
    Causalean.PO.POBackdoorSystem.Assumptions.integrable_factualY · Causalean/PO/ID/Exact/ATE.lean:313
  • propScore_ne_of_overlap lemma — From two-sided overlap, the per-arm propensity score P[D=d | σ(X)] is a.s. nonzero: for d = true directly from 0 < e(X), for d = false from e(X) < 1 via propScore false = 1 - e(X).
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    hov :
    ∀ᵐ ω ∂P.μ, 0 < S.propScore true ω ∧ S.propScore true ω < 1
    d :
    ∀ᵐ ω ∂P.μ, S.propScore d ω ≠ 0
    Proof (Lean source)
    lemma propScore_ne_of_overlap [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hov : ∀ᵐ ω ∂P.μ, 0 < S.propScore true ω ∧ S.propScore true ω < 1) (d : Bool) : ∀ᵐ ω ∂P.μ, S.propScore d ω ≠ 0 := by cases d · -- false: propScore false = 1 - propScore true, and propScore true < 1. have hindD_integrable : ∀ e : Bool, Integrable (S.dVar.indicator e) P.μ := fun e => S.dVar.integrable_indicator e (measurableSet_singleton e) have hsum_ptwise : (fun ω => S.dVar.indicator true ω + S.dVar.indicator false ω) = (fun _ : P.Ω => (1 : ℝ)) := by funext ω exact S.dVar.indicator_add_indicator_not ω have hsum : P.μ[fun ω => S.dVar.indicator true ω + S.dVar.indicator false ω | S.sigmaX] =ᵐ[P.μ] (fun _ => (1 : ℝ)) := by rw [hsum_ptwise] condexp_linearity have hadd : P.μ[fun ω => S.dVar.indicator true ω + S.dVar.indicator false ω | S.sigmaX] =ᵐ[P.μ] P.μ[S.dVar.indicator true | S.sigmaX] + P.μ[S.dVar.indicator false | S.sigmaX] := by condexp_linearity [hindD_integrable true, hindD_integrable false] filter_upwards [hsum, hadd, hov] with ω h1 h2 hT have heq : S.propScore true ω + S.propScore false ω = 1 := by have : P.μ[S.dVar.indicator true | S.sigmaX] ω + P.μ[S.dVar.indicator false | S.sigmaX] ω = 1 := by rw [← Pi.add_apply, ← h2, h1] unfold POBackdoorSystem.propScore exact this have hps_false : S.propScore false ω = 1 - S.propScore true ω := by linarith rw [hps_false] intro h linarith [hT.2] · filter_upwards [hov] with ω hω exact ne_of_gt hω.1
    Causalean.PO.POBackdoorSystem.propScore_ne_of_overlap · Causalean/PO/ID/Exact/ATE.lean:321
  • cate_backdoor_of_propScore_ne theorem — CATE-level backdoor identification (per-arm overlap form). The conditional ATE equals the adjusted-outcome functional under consistency, unconfoundedness, arm-wise outcome integrability, and the single one-sided requirement that the d-arm propensity score is a.s. nonzero (P[D=d | σ(X)] ≠ 0):
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    hcons :
    P.Consistency
    hunconf :
    P.CondIndepCF (RegimedVar.ofFactual S.dVar) S.cfBundle (RegimedVar.ofFactual S.xVar) P.μ
    hY1 :
    Integrable (S.YofD true) P.μ
    hY0 :
    Integrable (S.YofD false) P.μ
    d :
    h_ne :
    ∀ᵐ ω ∂P.μ, S.propScore d ω ≠ 0
    S.CATE d =ᵐ[P.μ] S.adjustedCE d
    Proof (Lean source)
    theorem cate_backdoor_of_propScore_ne [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hcons : P.Consistency) (hunconf : P.CondIndepCF (RegimedVar.ofFactual S.dVar) S.cfBundle (RegimedVar.ofFactual S.xVar) P.μ) (hY1 : Integrable (S.YofD true) P.μ) (hY0 : Integrable (S.YofD false) P.μ) (d : Bool) (h_ne : ∀ᵐ ω ∂P.μ, S.propScore d ω ≠ 0) : S.CATE d =ᵐ[P.μ] S.adjustedCE d := by -- Rewrite `adjustedCE d = condExpRatio S.xVar (factualY * indD d) (indD d) P.μ`. have hratio_def : S.adjustedCE d = S.xVar.condExpRatio (fun ω => S.factualY ω * S.dVar.indicator d ω) (S.dVar.indicator d) P.μ := by funext ω unfold POBackdoorSystem.adjustedCE POBackdoorSystem.propScore POBackdoorSystem.sigmaX POBackdoorSystem.factualX POVar.condExpRatio POVar.condExpGiven rfl rw [hratio_def] -- Apply `condExpRatio_eq_of_mul` to reduce to (hprod) and (hne). refine (S.xVar.condExpRatio_eq_of_mul (g := fun ω => S.factualY ω * S.dVar.indicator d ω) (h := S.dVar.indicator d) (target := S.CATE d) ?_ ?_).symm · -- (hprod): μ[Y·1_{D=d}|σX] =ᵐ μ[1_{D=d}|σX] · CATE d. -- Integrability prerequisites. have hindD_integrable : Integrable (S.dVar.indicator d) P.μ := by fun_prop have hYofD_integrable : Integrable (S.YofD d) P.μ := by cases d · exact hY0 · exact hY1 have hYofD_bdd_integrable_aux : Integrable (fun ω => S.YofD d ω * S.dVar.indicator d ω) P.μ := by fun_prop have hYtimesInd_integrable : Integrable (fun ω => S.factualY ω * S.dVar.indicator d ω) P.μ := by exact S.dVar.integrable_mul_indicator d (measurableSet_singleton d) (S.integrable_factualY_of_consistency hcons hY1 hY0) -- Step 1: μ[Y·1_{D=d}|σX] =ᵐ μ[Y(d)·1_{D=d}|σX]. have hstep1 : S.xVar.condExpGiven (fun ω => S.factualY ω * S.dVar.indicator d ω) P.μ =ᵐ[P.μ] S.xVar.condExpGiven (fun ω => S.YofD d ω * S.dVar.indicator d ω) P.μ := by have hvw : S.yVar.v ≠ S.dVar.v := Ne.symm S.hDY have hfm := POVar.factual_mul_indicator_eq_cfUnder_mul_indicator_fn hcons S.yVar S.dVar d hvw -- `S.factualY = S.yVar.factual` and `S.YofD d = S.yVar.cfUnder S.dVar d` by def. change S.xVar.condExpGiven (fun ω => S.yVar.factual ω * S.dVar.indicator d ω) P.μ =ᵐ[P.μ] S.xVar.condExpGiven (fun ω => S.yVar.cfUnder S.dVar d ω * S.dVar.indicator d ω) P.μ rw [hfm] refine hstep1.trans ?_ -- Project unconfoundedness onto the `d`-th coordinate of the bundle. -- The bundle has two components: index 0 = YofD true, index 1 = YofD false. let ψ : (∀ i : Fin S.cfBundle.n, S.cfBundle.type i) → ℝ := fun f => match d with | true => f (0 : Fin 2) | false => f (1 : Fin 2) have hψ_meas : Measurable ψ := by let instCf : ∀ a : Fin 2, MeasurableSpace (S.cfBundle.type a) := fun a => S.cfBundle.inst a cases d with | true => exact measurable_pi_apply (0 : Fin 2) | false => exact measurable_pi_apply (1 : Fin 2) have hYofD_eq : S.YofD d = ψ ∘ S.cfBundle.jointValue := by funext ω; cases d <;> rfl have hCI : CondIndepFun S.sigmaX S.sigmaX_le S.factualD (S.YofD d) P.μ := by have hproj := hunconf.project (ψ := ψ) hψ_meas rw [hYofD_eq]; exact hproj -- Apply factorization with u := indD d (as a function of factualD) and v := YofD d. -- Use the plain pointwise product: indD d ω * YofD d ω. have hindMul_swap : (fun ω => S.YofD d ω * S.dVar.indicator d ω) = (fun ω => S.dVar.indicator d ω * S.YofD d ω) := by funext ω; exact mul_comm _ _ rw [hindMul_swap] -- Apply via an auxiliary lemma that takes the (u, v) shapes matching our data. -- Use `condExp_mul_of_condIndep` with: -- f = factualD, g = YofD d, u = (fun b => if b = d then 1 else 0), v = id. -- `u (factualD ω) = indD d ω` and `id (YofD d ω) = YofD d ω` by rfl. -- Set-indicator packaging: `u b := ({d} : Set Bool).indicator 1 b`, which -- satisfies `u (S.factualD ω) = S.dVar.indicator d ω`. let u : Bool → ℝ := ({d} : Set Bool).indicator (fun _ => (1 : ℝ)) have hu_meas : Measurable u := by fun_prop have hu_eq : (fun ω => u (S.factualD ω)) = S.dVar.indicator d := by funext ω unfold POVar.indicator by_cases h : S.factualD ω = d · have h1 : S.factualD ω ∈ ({d} : Set Bool) := h have h2 : ω ∈ S.dVar.event d := h rw [show u (S.factualD ω) = (1 : ℝ) from Set.indicator_of_mem h1 _, Set.indicator_of_mem h2] · have h1 : S.factualD ω ∉ ({d} : Set Bool) := h have h2 : ω ∉ S.dVar.event d := h rw [show u (S.factualD ω) = (0 : ℝ) from Set.indicator_of_notMem h1 _, Set.indicator_of_notMem h2] have huMul_int : Integrable (fun ω => u (S.factualD ω) * S.YofD d ω) P.μ := by fun_prop have hfact : P.μ[fun ω => u (S.factualD ω) * S.YofD d ω | S.sigmaX] =ᵐ[P.μ] P.μ[fun ω => u (S.factualD ω) | S.sigmaX] * P.μ[fun ω => S.YofD d ω | S.sigmaX] := by have := condExp_mul_of_condIndep (μ := P.μ) (m := S.sigmaX) S.sigmaX_le (f := S.factualD) (g := S.YofD d) S.measurable_factualD (S.measurable_YofD d) hCI (u := u) (v := id) hu_meas measurable_id (by rw [hu_eq]; exact hindD_integrable) hYofD_integrable huMul_int exact this -- Goal (after hindMul_swap): -- S.xVar.condExpGiven (indD d * YofD d) =ᵐ S.xVar.condExpGiven (indD d) * CATE d. -- Unfold condExpGiven/CATE to land on μ[·|σX] with matching argument shapes. unfold POVar.condExpGiven POBackdoorSystem.CATE POBackdoorSystem.sigmaX POBackdoorSystem.factualX have hfact_rw : (fun ω => u (S.factualD ω)) = S.dVar.indicator d := hu_eq have hprod_rw : (fun ω => u (S.factualD ω) * S.YofD d ω) = (fun ω => S.dVar.indicator d ω * S.YofD d ω) := by funext ω; rw [congr_fun hu_eq ω] rw [hprod_rw, hfact_rw] at hfact exact hfact · -- (hne): μ[1_{D=d}|σX] ≠ 0 a.s. — supplied directly as `h_ne`. -- `S.xVar.condExpGiven (S.dVar.indicator d) P.μ = S.propScore d` definitionally. have hEq : S.xVar.condExpGiven (S.dVar.indicator d) P.μ = S.propScore d := by unfold POVar.condExpGiven POBackdoorSystem.propScore POBackdoorSystem.sigmaX POBackdoorSystem.factualX rfl rw [hEq] exact h_ne
    Causalean.PO.POBackdoorSystem.cate_backdoor_of_propScore_ne · Causalean/PO/ID/Exact/ATE.lean:361
  • measurable_factualDX lemma — The observed treatment-covariate pair is measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualDX
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualDX : Measurable S.factualDX := S.measurable_factualD.prodMk S.measurable_factualX
    Causalean.PO.POBackdoorSystem.measurable_factualDX · Causalean/PO/ID/Exact/ATE.lean:556
  • sigmaDX_le lemma — The joint treatment-covariate sigma-algebra is a sub-sigma-algebra of the ambient one.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    S.sigmaDX ≤ (inferInstance : MeasurableSpace P.Ω)
    Proof (Lean source)
    lemma sigmaDX_le : S.sigmaDX ≤ (inferInstance : MeasurableSpace P.Ω) := S.measurable_factualDX.comap_le
    Causalean.PO.POBackdoorSystem.sigmaDX_le · Causalean/PO/ID/Exact/ATE.lean:567
  • measurable_factualDX_sigmaDX lemma — The observed treatment-covariate pair is measurable for the joint sigma-algebra it generates.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable[S.sigmaDX] S.factualDX
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualDX_sigmaDX : Measurable[S.sigmaDX] S.factualDX := comap_measurable S.factualDX
    Causalean.PO.POBackdoorSystem.measurable_factualDX_sigmaDX · Causalean/PO/ID/Exact/ATE.lean:571
  • measurable_factualD_sigmaDX lemma — The observed treatment is measurable for the joint treatment-covariate sigma-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable[S.sigmaDX] S.factualD
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualD_sigmaDX : Measurable[S.sigmaDX] S.factualD := measurable_fst.comp (comap_measurable S.factualDX)
    Causalean.PO.POBackdoorSystem.measurable_factualD_sigmaDX · Causalean/PO/ID/Exact/ATE.lean:577
  • measurable_factualX_sigmaDX lemma — The observed covariate is measurable for the joint treatment-covariate sigma-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable[S.sigmaDX] S.factualX
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualX_sigmaDX : Measurable[S.sigmaDX] S.factualX := measurable_snd.comp (comap_measurable S.factualDX)
    Causalean.PO.POBackdoorSystem.measurable_factualX_sigmaDX · Causalean/PO/ID/Exact/ATE.lean:583
  • sigmaX_le_sigmaDX lemma — σ(X) ≤ σ(D, X): the covariate σ-algebra is coarser than the joint one.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    S.sigmaX ≤ S.sigmaDX
    Proof (Lean source)
    lemma sigmaX_le_sigmaDX : S.sigmaX ≤ S.sigmaDX := by -- `factualX = sndfactualDX`, so `comap factualX ≤ comap factualDX`. have hfx : S.factualX = snd ∘ S.factualDX := rfl rw [POBackdoorSystem.sigmaX, POBackdoorSystem.sigmaDX, hfx, ← MeasurableSpace.comap_comp] exact comap_mono measurable_snd.comap_le
    Causalean.PO.POBackdoorSystem.sigmaX_le_sigmaDX · Causalean/PO/ID/Exact/ATE.lean:589
  • stronglyMeasurable_outcomeReg lemma — The observed outcome regression is strongly measurable with respect to the joint treatment-covariate sigma-algebra.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    StronglyMeasurable[S.sigmaDX] S.outcomeReg
    Proof (Lean source)
    @[fun_prop] lemma stronglyMeasurable_outcomeReg : StronglyMeasurable[S.sigmaDX] S.outcomeReg := MeasureTheory.stronglyMeasurable_condExp
    Causalean.PO.POBackdoorSystem.stronglyMeasurable_outcomeReg · Causalean/PO/ID/Exact/ATE.lean:605
  • measurable_outcomeReg lemma — The observed outcome regression is measurable for the ambient sigma-algebra on the sample space.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.outcomeReg
    Proof (Lean source)
    @[fun_prop] lemma measurable_outcomeReg : Measurable S.outcomeReg := (S.stronglyMeasurable_outcomeReg.measurable).mono S.sigmaDX_le le_rfl
    Causalean.PO.POBackdoorSystem.measurable_outcomeReg · Causalean/PO/ID/Exact/ATE.lean:612
  • exists_regFn lemma — The σ(D, X)-measurable outcomeReg factors through (D, X): there is a measurable value-space regression function r : Bool × γ → ℝ with outcomeReg = r ∘ factualDX. This is Doob–Dynkin (exists_eq_measurable_comp); r is the function an ML regressor of Y on (D, X) targets.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    ∃ r : Bool × γ → ℝ,
    conclusion 1
    conclusion 2
    S.outcomeReg = fun ω => r (S.factualDX ω)
    Proof (Lean source)
    lemma exists_regFn : ∃ r : Bool × γ → ℝ, Measurable r ∧ S.outcomeReg = fun ω => r (S.factualDX ω) := by -- `sigmaDX = comap factualDX`, so `outcomeReg` is `comap factualDX`-measurable; -- Doob–Dynkin (`exists_eq_measurable_comp`) produces the value-space factorisation. have hmeas : Measurable[S.sigmaDX] S.outcomeReg := by fun_prop obtain ⟨r, hr_meas, hr_eq⟩ := Measurable.exists_eq_measurable_comp (f := S.factualDX) (g := S.outcomeReg) hmeas exact ⟨r, hr_meas, by funext ω; exact congrFun hr_eq ω⟩
    Causalean.PO.POBackdoorSystem.exists_regFn · Causalean/PO/ID/Exact/ATE.lean:618
  • measurable_regFn lemma — The value-space outcome regression is measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.regFn
    Proof (Lean source)
    @[fun_prop] lemma measurable_regFn : Measurable S.regFn := S.exists_regFn.choose_spec.1
    Causalean.PO.POBackdoorSystem.measurable_regFn · Causalean/PO/ID/Exact/ATE.lean:635
  • outcomeReg_eq_regFn lemma — The observed outcome regression equals the value-space regression evaluated at each unit's observed treatment and covariate.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    S.outcomeReg = fun ω => S.regFn (S.factualDX ω)
    Proof (Lean source)
    lemma outcomeReg_eq_regFn : S.outcomeReg = fun ω => S.regFn (S.factualDX ω) := S.exists_regFn.choose_spec.2
    Causalean.PO.POBackdoorSystem.outcomeReg_eq_regFn · Causalean/PO/ID/Exact/ATE.lean:639
  • exists_propScoreLift lemma — The σ(X)-measurable propensity propScore true factors through factualX: a measurable value-space propensity e : γ → ℝ with propScore true = e ∘ factualX (Doob–Dynkin). This is the value-space propensity an estimator learns.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    ∃ e : γ → ℝ,
    conclusion 1
    conclusion 2
    S.propScore true = fun ω => e (S.factualX ω)
    Proof (Lean source)
    lemma exists_propScoreLift : ∃ e : γ → ℝ, Measurable e ∧ S.propScore true = fun ω => e (S.factualX ω) := by have hmeas : Measurable[S.sigmaX] (S.propScore true) := by fun_prop obtain ⟨e, he_meas, he_eq⟩ := Measurable.exists_eq_measurable_comp (f := S.factualX) (g := S.propScore true) hmeas exact ⟨e, he_meas, by funext ω; exact congrFun he_eq ω⟩
    Causalean.PO.POBackdoorSystem.exists_propScoreLift · Causalean/PO/ID/Exact/ATE.lean:645
  • measurable_eLift lemma — The value-space propensity representative is measurable.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    Measurable S.eLift
    Proof (Lean source)
    @[fun_prop] lemma measurable_eLift : Measurable S.eLift := S.exists_propScoreLift.choose_spec.1
    Causalean.PO.POBackdoorSystem.measurable_eLift · Causalean/PO/ID/Exact/ATE.lean:658
  • propScore_true_eq_eLift lemma — The treated-arm propensity score equals the value-space propensity evaluated at each unit's observed covariate.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    S.propScore true = fun ω => S.eLift (S.factualX ω)
    Proof (Lean source)
    lemma propScore_true_eq_eLift : S.propScore true = fun ω => S.eLift (S.factualX ω) := S.exists_propScoreLift.choose_spec.2
    Causalean.PO.POBackdoorSystem.propScore_true_eq_eLift · Causalean/PO/ID/Exact/ATE.lean:662
  • regression_adjustment_of_assumptions theorem — Regression-adjustment, packaged for identified systems. The same observable identity adjustedCE d =ᵐ E[Y|D=d,X], with the two regularity hypotheses of regression_adjustment discharged from the back-door Assumptions: integrability of the observed outcome from Assumptions.integrable_factualY, and overlap from propScore_ne_of_overlap. Lets callers in an identified context apply it with just hA.
    P :
    shared
    γ :
    Type u_1
    shared
    S :
    shared
    hA :
    S.Assumptions
    d :
    S.adjustedCE d =ᵐ[P.μ] (fun ω => S.regFn (d, S.factualX ω))
    Proof (Lean source)
    theorem regression_adjustment_of_assumptions [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.Assumptions) (d : Bool) : S.adjustedCE d =ᵐ[P.μ] (fun ω => S.regFn (d, S.factualX ω)) := S.regression_adjustment d hA.integrable_factualY (S.propScore_ne_of_overlap hA.overlap d)
    Causalean.PO.POBackdoorSystem.regression_adjustment_of_assumptions · Causalean/PO/ID/Exact/ATE.lean:781
ATT 6 core · 6 supporting This file identifies the average treatment effect on the treated from observed data under back-door assumptions, expressing the causal target through covariate-adjusted treated outcomes and an equivalent augmented invers ★ ATT_eq_adjustedATT★ adjustedATT_eq_aipwForm

This file identifies the average treatment effect on the treated from observed data under back-door assumptions, expressing the causal target through covariate-adjusted treated outcomes and an equivalent augmented inverse-probability weighted form.

It reuses POBackdoorSystem from the ATE file but weakens the overlap requirement to the control arm. The public API includes ATTAssumptions, ATT_eq_adjustedATT, and adjustedATT_eq_aipwForm, respectively packaging the one-sided assumptions, the adjusted ATT identification theorem, and the AIPW representation.

def propTreated reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the marginal treatment probability is the population mean of the indicator for the treated arm.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
propTreated S :
∫ ω, S.dVar.indicator true ω ∂P.μ
Causalean.PO.POBackdoorSystem.propTreated · Causalean/PO/ID/Exact/ATT.lean:45 · uses POBackdoorSystem , POSystem
def ATT reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the average treatment effect on the treated is the population mean treatment effect weighted by the treated-arm indicator and divided by the marginal treatment probability. It is ATT = E[A · (Y(1) − Y(0))] / π_T.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
ATT S :
(∫ ω, S.dVar.indicator true ω * (S.YofD true ω - S.YofD false ω) ∂P.μ) / S.propTreated
Causalean.PO.POBackdoorSystem.ATT · Causalean/PO/ID/Exact/ATT.lean:49 · uses POBackdoorSystem , POSystem
def adjustedATT reviewed
Causalean.PO.POBackdoorSystem

Given a binary-treatment backdoor system, the adjusted average treatment effect on the treated is the treated-indicator-weighted population mean of factual outcome minus the adjusted control conditional functional, divided by the marginal treatment probability. It is the observable, control-regression form: E[A · (Y − μ₀(X))] / π_T. Only the CONTROL regression μ₀(X) = adjustedCE false appears — the treated potential outcome is observed directly on {D = 1} via consistency (A · Y = A · Y(1)), so no treated regression μ₁(X) and hence no 0 < e(X) is needed. This is the standard ATT estimand and requires only one-sided overlap e(X) < 1. The AIPW form is recovered as a corollary (adjustedATT_eq_aipwForm).

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
shared
adjustedATT S :
(∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) ∂P.μ) / S.propTreated
Causalean.PO.POBackdoorSystem.adjustedATT · Causalean/PO/ID/Exact/ATT.lean:55 · uses POBackdoorSystem , POSystem
structure ATTAssumptions reviewed
Causalean.PO.POBackdoorSystem

Backdoor assumptions for ATT identification. These are the standard ATT conditions, with overlap required on only one side — every covariate stratum keeps a positive chance of the control arm (e(X) < 1) — which is strictly weaker than the two-sided overlap the ATE needs, because on the treated the outcome is observed directly.

Definition (Lean source)
P :
shared
γ :
Type u_1
shared
S :
consistency :
P.Consistency

Consistency (SUTVA): on {D = d}, the observed outcome equals Y(d).

unconfoundedness :
P.CondIndepCF (RegimedVar.ofFactual S.dVar) S.cfBundle (RegimedVar.ofFactual S.xVar) P.μ

Unconfoundedness: D ⟂ (Y(1), Y(0)) | X, as conditional independence of the realized D and the counterfactual bundle given σ(X).

overlapControl :
∀ᵐ ω ∂P.μ, S.propScore true ω < 1

One-sided overlap (control common support): P[D=1 | σ(X)] < 1 a.s. Only the upper bound is needed for ATT — the treated arm is observed directly.

integrable_Y1 :
Integrable (S.YofD true) P.μ

Regularity: the treated potential outcome Y(1) is integrable.

integrable_Y0 :
Integrable (S.YofD false) P.μ

Regularity: the control potential outcome Y(0) is integrable.

propTreated_pos :
0 < S.propTreated

Positivity of the marginal treatment probability π_T = P[D=1].

Causalean.PO.POBackdoorSystem.ATTAssumptions · Causalean/PO/ID/Exact/ATT.lean:66 · uses POBackdoorSystem , POSystem
theorem ATT_eq_adjustedATT reviewed
Causalean.PO.POBackdoorSystem

ATT identification (one-sided overlap). Under consistency, unconfoundedness, one-sided overlap (e(X) < 1, the control arm), and positivity of the marginal treatment probability, the potential-outcome-level average treatment effect on the treated equals the observable adjusted-ATT functional:

Formal statement
P :
shared
γ :
Type u_1
shared
S :
shared
hA :
S.ATTAssumptions
S.ATT = S.adjustedATT
Proof (Lean source)
theorem ATT_eq_adjustedATT [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.ATTAssumptions) : S.ATT = S.adjustedATT := by unfold POBackdoorSystem.ATT POBackdoorSystem.adjustedATT congr 1 have hfalse := S.att_numerator_arm hA false (S.cate_backdoor_control hA) (S.integrable_adjustedCE_control hA) have hY1 : Integrable (fun ω => S.dVar.indicator true ω * S.YofD true ω) P.μ := by fun_prop have hY0 : Integrable (fun ω => S.dVar.indicator true ω * S.YofD false ω) P.μ := by fun_prop have hAfact : Integrable (fun ω => S.dVar.indicator true ω * S.factualY ω) P.μ := by fun_prop have hAdj0 : Integrable (fun ω => S.dVar.indicator true ω * S.adjustedCE false ω) P.μ := by fun_prop -- On the treated set, consistency gives `A · Y = A · Y(1)`. have hcons : (fun ω => S.dVar.indicator true ω * S.factualY ω) = (fun ω => S.dVar.indicator true ω * S.YofD true ω) := by have hfm := POVar.factual_mul_indicator_eq_cfUnder_mul_indicator_fn hA.consistency S.yVar S.dVar true (Ne.symm S.hDY) funext ω have hω := congr_fun hfm ω change S.dVar.indicator true ω * S.factualY ω = S.dVar.indicator true ω * S.YofD true ω rw [mul_comm (S.dVar.indicator true ω) (S.factualY ω), mul_comm (S.dVar.indicator true ω) (S.YofD true ω)] exact hω calc ∫ ω, S.dVar.indicator true ω * (S.YofD true ω - S.YofD false ω) ∂P.μ = ∫ ω, (S.dVar.indicator true ω * S.YofD true ω) - (S.dVar.indicator true ω * S.YofD false ω) ∂P.μ := by congr with ω ring _ = (∫ ω, S.dVar.indicator true ω * S.YofD true ω ∂P.μ) - (∫ ω, S.dVar.indicator true ω * S.YofD false ω ∂P.μ) := by exact MeasureTheory.integral_sub hY1 hY0 _ = (∫ ω, S.dVar.indicator true ω * S.factualY ω ∂P.μ) - (∫ ω, S.dVar.indicator true ω * S.adjustedCE false ω ∂P.μ) := by rw [← MeasureTheory.integral_congr_ae (Filter.EventuallyEq.of_eq hcons), hfalse] _ = ∫ ω, (S.dVar.indicator true ω * S.factualY ω) - (S.dVar.indicator true ω * S.adjustedCE false ω) ∂P.μ := by exact (MeasureTheory.integral_sub hAfact hAdj0).symm _ = ∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) ∂P.μ := by congr with ω ring
theorem adjustedATT_eq_aipwForm reviewed
Causalean.PO.POBackdoorSystem

AIPW corollary. Under the ATT identification assumptions — consistency, unconfoundedness, one-sided control-arm overlap, and a positive marginal treatment probability, provided the observed inverse-propensity-weighted correction term is integrable, the adjustedATT functional equals its augmented inverse-propensity-weighted (AIPW) form:

Formal statement
P :
shared
γ :
Type u_1
shared
S :
shared
hA :
S.ATTAssumptions
hIPW :
Integrable (fun ω => (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω)) P.μ
S.adjustedATT
= ((∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) - (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ)) / S.propTreated
Proof (Lean source)
theorem adjustedATT_eq_aipwForm [StandardBorelSpace P.Ω] [IsFiniteMeasure P.μ] (hA : S.ATTAssumptions) (hIPW : Integrable (fun ω => (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω)) P.μ) : S.adjustedATT = ((∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) - (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ)) / S.propTreated := by let W : P.Ω → ℝ := fun ω => S.propScore true ω / (1 - S.propScore true ω) let R : P.Ω → ℝ := fun ω => S.factualY ω - S.adjustedCE false ω have hW_sm : StronglyMeasurable[S.sigmaX] W := by fun_prop have hfalse_indicator : ∀ ω, 1 - S.dVar.indicator true ω = S.dVar.indicator false ω := by intro ω have hsum := S.dVar.indicator_add_indicator_not ω linarith have hIPW_weighted : Integrable (fun ω => W ω * (S.dVar.indicator false ω * R ω)) P.μ := by refine hIPW.congr ?_ refine Filter.Eventually.of_forall (fun ω => ?_) unfold W R change (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) = S.propScore true ω / (1 - S.propScore true ω) * (S.dVar.indicator false ω * (S.factualY ω - S.adjustedCE false ω)) rw [hfalse_indicator ω] ring have hIPW_zero : ∫ ω, (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ = 0 := by have hweighted_zero := S.weighted_false_residual_integral_zero hA W hW_sm hIPW_weighted calc ∫ ω, (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ = ∫ ω, W ω * (S.dVar.indicator false ω * R ω) ∂P.μ := by apply MeasureTheory.integral_congr_ae refine Filter.Eventually.of_forall (fun ω => ?_) unfold W R change (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) = S.propScore true ω / (1 - S.propScore true ω) * (S.dVar.indicator false ω * (S.factualY ω - S.adjustedCE false ω)) rw [hfalse_indicator ω] ring _ = 0 := hweighted_zero have htreated_int : Integrable (fun ω => S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω)) P.μ := by fun_prop have hnumer : ∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) - (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ = ∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) ∂P.μ := by calc ∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) - (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ = (∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) ∂P.μ) - ∫ ω, (1 - S.dVar.indicator true ω) * (S.propScore true ω / (1 - S.propScore true ω)) * (S.factualY ω - S.adjustedCE false ω) ∂P.μ := by exact MeasureTheory.integral_sub htreated_int hIPW _ = ∫ ω, S.dVar.indicator true ω * (S.factualY ω - S.adjustedCE false ω) ∂P.μ := by rw [hIPW_zero, sub_zero] unfold POBackdoorSystem.adjustedATT congr 1 exact hnumer.symm
6 supporting declarations (lemmas, instances)
CSDID 19 core · 13 supporting This file develops the potential-outcome setup for Callaway-Sant'Anna group-time treatment effects. ★ POCSDIDSystem★ att_csdid

Staggered-Adoption Difference-in-Differences

This file develops the potential-outcome setup for Callaway-Sant'Anna group-time treatment effects. It encodes treatment cohorts, never-treated comparisons, and the assumptions needed to identify the average treatment effect for a cohort at a time period.

It extends two-period DID to a finite horizon with first-treated cohorts and a never-treated comparison group. Periods are zero-indexed, so admissible group-time effects use a cohort after the first period and an outcome period no earlier than that cohort.

The central definitions are regOf, regNT, cohortEvent, neverTreatedEvent, and the group-time estimand ATT; the main theorem att_csdid proves the observable group-time DID contrast under the Callaway-Sant'Anna assumptions.

structure POCSDIDSystem reviewed
Causalean.PO

A staggered-adoption DID system has a binary treatment variable at each of T periods, where at least two periods are observed, together with a real outcome variable at each period, such that the treatment nodes are pairwise distinct across periods and likewise for the outcome nodes, and no treatment node coincides with any outcome node.

Definition (Lean source)
P :
T :
hT :
2 ≤ T
D :
Fin T → P.V
Y :
Fin T → P.V
hDbool :
∀ s : Fin T, P.X (D s) ≃ᵐ Bool
hYreal :
∀ s : Fin T, P.X (Y s) ≃ᵐ ℝ
hDinj :
hYinj :
hDY :
∀ s t : Fin T, D s ≠ Y t
Causalean.PO.POCSDIDSystem · Causalean/PO/ID/Exact/CSDID.lean:47 · uses POSystem
def dVar reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and a period, the binary treatment potential-outcome variable is the treatment node for that period.

Definition (Lean source)
P :
shared
S :
shared
s :
Fin S.T
dVar S s :
⟨S.D s, S.hDbool s⟩
def yVar reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and a period, the real-valued outcome potential-outcome variable is the outcome node for that period.

Definition (Lean source)
P :
shared
S :
shared
s :
Fin S.T
yVar S s :
POVar P ℝ
⟨S.Y s, S.hYreal s⟩
def factualD reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and a period, the factual treatment function assigns each unit its observed treatment at that period.

Definition (Lean source)
P :
shared
S :
shared
s :
Fin S.T
factualD S s :
P.Ω → Bool
(S.dVar s).factual
Causalean.PO.POCSDIDSystem.factualD · Causalean/PO/ID/Exact/CSDID.lean:79 · uses POCSDIDSystem , POSystem
def factualY reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and a period, the factual outcome function assigns each unit its observed outcome at that period.

Definition (Lean source)
P :
shared
S :
shared
s :
Fin S.T
factualY S s :
P.Ω → ℝ
(S.yVar s).factual
Causalean.PO.POCSDIDSystem.factualY · Causalean/PO/ID/Exact/CSDID.lean:83 · uses POCSDIDSystem , POSystem
def dEvent reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, a period, and a binary treatment value, the period-specific treatment event is the set of units whose observed treatment at that period equals that value.

Definition (Lean source)
P :
shared
S :
shared
s :
Fin S.T
b :
dEvent S s b :
Set P.Ω
(S.dVar s).event b
Causalean.PO.POCSDIDSystem.dEvent · Causalean/PO/ID/Exact/CSDID.lean:87 · uses POCSDIDSystem , POSystem
def dTargetUpTo reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, the treatment-target-set function maps each cutoff to the empty set at cutoff zero and the treatment nodes from periods strictly before the cutoff at every positive cutoff.

Definition (Lean source)
P :
shared
dTargetUpTo S :
ℕ → Finset P.V
clause 1
| 0 => ∅
clause 2
| k + 1 => if h : k < S.T then insert (S.D ⟨k, h⟩) (S.dTargetUpTo k) else S.dTargetUpTo k
Causalean.PO.POCSDIDSystem.dTargetUpTo · Causalean/PO/ID/Exact/CSDID.lean:114 · uses POCSDIDSystem , POSystem
def regUpToAux reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, a binary treatment path over all periods, a cutoff, and proof that the cutoff does not exceed the horizon, the partial treatment-path regime together with its target-set identity fixes treatments before the cutoff according to that path and has exactly the treatment nodes before the cutoff as its target.

Definition (Lean source)
P :
shared
b :
Fin S.T → Bool
k :
k ≤ S.T
regUpToAux S b k :
{ r : Regime P.V P.X // r.target = S.dTargetUpTo k }
clause 1
| 0, _ => ⟨Regime.empty, by simp [dTargetUpTo, Regime.empty]⟩
clause 2
| k + 1, h
=> have hk : k < S.T := h let pair := S.regUpToAux b k (le_of_lt hk) let r_rec : Regime P.V P.X := pair.1 have hrec : r_rec.target = S.dTargetUpTo k := pair.2 let v := S.D ⟨k, hk⟩ have hv_not : v ∉ r_rec.target := by rw [hrec] intro hmem rcases (S.dTargetUpTo_mem_iff k (le_of_lt hk) _).mp hmem with ⟨i, hi, heq⟩ have hFin : (⟨k, hk⟩ : Fin S.T) = i := S.hDinj heq have hval : (k : ℕ) = i.val := by have := congrArg val hFin; simpa using this omega let r_new := Regime.sqcup (Regime.single v ((S.hDbool ⟨k, hk⟩).symm (b ⟨k, hk⟩))) r_rec (Regime.single_disjoint_of_not_mem _ _ hv_not) ⟨r_new, by show r_new.target = S.dTargetUpTo (k + 1) simp only [r_new, Regime.sqcup_target, Regime.single_target, dTargetUpTo, hk, ↓reduceDIte] rw [hrec] ext w; simp [Finset.mem_insert, v]⟩
def regimeBy reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and a binary treatment path over all periods, the full-horizon treatment regime fixes every period's treatment to the corresponding value on that path.

Definition (Lean source)
P :
shared
b :
Fin S.T → Bool
regimeBy S b :
Regime P.V P.X
(S.regUpToAux b S.T (le_refl _)).1
Causalean.PO.POCSDIDSystem.regimeBy · Causalean/PO/ID/Exact/CSDID.lean:179 · uses POCSDIDSystem , POSystem , Regime
def regOf reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and a cohort period, the cohort treatment regime leaves all earlier periods untreated and fixes treatment to true in that cohort period and every later period.

Definition (Lean source)
P :
shared
S :
shared
g :
Fin S.T
regOf S g :
Regime P.V P.X
S.regimeBy (fun s => decide (g.val ≤ s.val))
def regNT reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, the never-treated regime fixes treatment to false in every period.

Definition (Lean source)
P :
shared
S :
shared
regNT S :
Regime P.V P.X
S.regimeBy (fun _ => false)
def YofCohort reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, an outcome period, and a cohort period, the cohort potential-outcome function assigns each unit its outcome at that period under the treatment path that begins in the cohort period.

Definition (Lean source)
P :
shared
S :
shared
t g :
Fin S.T
YofCohort S t g :
P.Ω → ℝ
(S.yVar t).cf (S.regOf g)
Causalean.PO.POCSDIDSystem.YofCohort · Causalean/PO/ID/Exact/CSDID.lean:229 · uses POCSDIDSystem , POSystem
def YofNT reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system and an outcome period, the never-treated potential-outcome function assigns each unit its outcome at that period under the regime that never treats.

Definition (Lean source)
P :
shared
S :
shared
t :
Fin S.T
YofNT S t :
P.Ω → ℝ
(S.yVar t).cf S.regNT
Causalean.PO.POCSDIDSystem.YofNT · Causalean/PO/ID/Exact/CSDID.lean:235 · uses POCSDIDSystem , POSystem
def predFin reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, a cohort period, and proof that the cohort is not the first period, the predecessor period is the period immediately before that cohort.

Definition (Lean source)
P :
shared
S :
shared
g :
Fin S.T
_hg :
1 ≤ g.val
predFin S g _hg :
Fin S.T
⟨g.val - 1, lt_of_le_of_lt (Nat.sub_le _ _) g.isLt⟩
Causalean.PO.POCSDIDSystem.predFin · Causalean/PO/ID/Exact/CSDID.lean:251 · uses POCSDIDSystem , POSystem
def cohortEvent reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, a cohort period, and proof that it is not the first period, the cohort event is the set of units untreated immediately before that period and treated in that period.

Definition (Lean source)
P :
shared
S :
shared
g :
Fin S.T
hg :
1 ≤ g.val
cohortEvent S g hg :
Set P.Ω
S.dEvent (S.predFin g hg) false ∩ S.dEvent g true
Causalean.PO.POCSDIDSystem.cohortEvent · Causalean/PO/ID/Exact/CSDID.lean:257 · uses POCSDIDSystem , POSystem
def neverTreatedEvent reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, the never-treated event is the set of units whose observed treatment is false in every period.

Definition (Lean source)
P :
shared
S :
shared
neverTreatedEvent S :
Set P.Ω
⋂ s : Fin S.T, S.dEvent s false
Causalean.PO.POCSDIDSystem.neverTreatedEvent · Causalean/PO/ID/Exact/CSDID.lean:268 · uses POCSDIDSystem , POSystem
def ATT reviewed
Causalean.PO.POCSDIDSystem

For a staggered-adoption DID system, a cohort period, an outcome period, and proof that the cohort is not the first period, the group-time average treatment effect on the treated is the cohort-event conditional mean of the period-tt difference between the cohort and never-treated potential outcomes.

Definition (Lean source)
P :
shared
S :
shared
g t :
Fin S.T
hg :
1 ≤ g.val
ATT S g t hg :
eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.YofCohort t g ω - S.YofNT t ω)
Causalean.PO.POCSDIDSystem.ATT · Causalean/PO/ID/Exact/CSDID.lean:276 · uses POCSDIDSystem , POSystem
structure Assumptions reviewed
Causalean.PO.POCSDIDSystem

The Callaway-Sant'Anna assumptions combine consistency of the underlying potential-outcome system: no unit is treated at period zero and once treated, a unit remains treated in every later period (irreversible adoption); pre-treatment outcomes do not anticipate future treatment; each cohort's mean untreated trend matches the never-treated group's mean untreated trend; each cohort and the never-treated group occur with positive, finite probability; and the cohort and never-treated potential outcomes are integrable.

Definition (Lean source)
P :
shared
consistency :
P.Consistency

Consistency of the underlying PO system.

irreversibilityBase :
∀ᵐ ω ∂P.μ, S.factualD ⟨0, lt_of_lt_of_le Nat.zero_lt_two S.hT⟩ ω = false

Irreversibility, base case: D_0 = 0 almost surely.

irreversibilityStep :
∀ (s : Fin S.T) (h : s.val + 1 < S.T),
∀ᵐ ω ∂P.μ, S.factualD s ω = true → S.factualD ⟨s.val + 1, h⟩ ω = true

Irreversibility, absorbing: D_s = 1 ⟹ D_{s+1} = 1 almost surely.

noAnticipation :
∀ (g s : Fin S.T)
if
s.val < g.val
then
∀ᵐ ω ∂P.μ, S.YofCohort s g ω = S.YofNT s ω

No anticipation: pre-treatment outcomes are unaffected by future treatment.

parallelTrends :
∀ (g t : Fin S.T) (hg : 1 ≤ g.val) (_hgt : g.val ≤ t.val),
eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.YofNT t ω - S.YofNT (S.predFin g hg) ω)
= eventCondExp P.μ S.neverTreatedEvent (fun ω => S.YofNT t ω - S.YofNT (S.predFin g hg) ω)

Never-treated parallel trends (long-difference form).

posCohort :
∀ (g : Fin S.T) (hg : 1 ≤ g.val),
P.μ (S.cohortEvent g hg) ≠ 0 ∧ P.μ (S.cohortEvent g hg) ≠ ⊤

Positivity of cohorts.

posNT :
P.μ S.neverTreatedEvent ≠ 0 ∧ P.μ S.neverTreatedEvent ≠ ⊤

Positivity of the never-treated event.

intYofCohort :
∀ g t : Fin S.T, Integrable (S.YofCohort t g) P.μ

Integrability of Y_t(g) for every cohort-period pair.

intYofNT :
∀ t : Fin S.T, Integrable (S.YofNT t) P.μ

Integrability of Y_t(∞).

Causalean.PO.POCSDIDSystem.Assumptions · Causalean/PO/ID/Exact/CSDID.lean:286 · uses POCSDIDSystem , POSystem
theorem att_csdid reviewed
Causalean.PO.POCSDIDSystem

Callaway--Sant'Anna group-time DID identification of ATT(g, t). Under the group-time assumptions — consistency, no-anticipation, and group-time parallel trends, for a treatment cohort g that starts treatment no earlier than period 1 and a calendar period t no earlier than g, the group-time average treatment effect on the treated equals the difference between the cohort-g mean outcome change from the period before g to period t and the corresponding mean outcome change for the never-treated group:

Formal statement
P :
shared
S :
shared
hA :
S.Assumptions
g t :
Fin S.T
hg :
1 ≤ g.val
hgt :
g.val ≤ t.val
S.ATT g t hg
= eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.factualY t ω - S.factualY (S.predFin g hg) ω)
- eventCondExp P.μ S.neverTreatedEvent (fun ω => S.factualY t ω - S.factualY (S.predFin g hg) ω)
Proof (Lean source)
theorem att_csdid (hA : S.Assumptions) (g t : Fin S.T) (hg : 1 ≤ g.val) (hgt : g.val ≤ t.val) : S.ATT g t hg = eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.factualY t ω - S.factualY (S.predFin g hg) ω) - eventCondExp P.μ S.neverTreatedEvent (fun ω => S.factualY t ω - S.factualY (S.predFin g hg) ω) := by have hPredLtG : (S.predFin g hg).val < g.val := by have : g.val - 1 < g.val := sub_lt (lt_of_lt_of_le Nat.zero_lt_one hg) Nat.zero_lt_one simpa [predFin] using this have hAE : (fun ω => S.YofCohort t g ω - S.YofNT t ω) =ᵐ[P.μ] fun ω => (S.YofCohort t g ω - S.YofCohort (S.predFin g hg) g ω) - (S.YofNT t ω - S.YofNT (S.predFin g hg) ω) := by refine (hA.noAnticipation g (S.predFin g hg) hPredLtG).mono (fun ω hω => ?_) change S.YofCohort t g ω - S.YofNT t ω = (S.YofCohort t g ω - S.YofCohort (S.predFin g hg) g ω) - (S.YofNT t ω - S.YofNT (S.predFin g hg) ω) rw [hω] ring have hATT_split : S.ATT g t hg = eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.YofCohort t g ω - S.YofCohort (S.predFin g hg) g ω) - eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.YofNT t ω - S.YofNT (S.predFin g hg) ω) := by unfold ATT rw [eventCondExp_congr_ae P.μ (S.cohortEvent g hg) (ae_restrict_of_ae hAE)] exact eventCondExp_sub P.μ (S.cohortEvent g hg) ((hA.intYofCohort g t).sub (hA.intYofCohort g (S.predFin g hg))).integrableOn ((hA.intYofNT t).sub (hA.intYofNT (S.predFin g hg))).integrableOn have h_first : eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.YofCohort t g ω - S.YofCohort (S.predFin g hg) g ω) = eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.factualY t ω - S.factualY (S.predFin g hg) ω) := by unfold eventCondExp rw [MeasureTheory.integral_congr_ae] rw [EventuallyEq, MeasureTheory.ae_restrict_iff' (S.measurableSet_cohortEvent g hg)] filter_upwards [S.factualY_eq_YofCohort_on_cohortEvent hA g t hg, S.factualY_eq_YofCohort_on_cohortEvent hA g (S.predFin g hg) hg] with ω ht hpred hω rw [ht hω, hpred hω] have h_pt : eventCondExp P.μ (S.cohortEvent g hg) (fun ω => S.YofNT t ω - S.YofNT (S.predFin g hg) ω) = eventCondExp P.μ S.neverTreatedEvent (fun ω => S.YofNT t ω - S.YofNT (S.predFin g hg) ω) := hA.parallelTrends g t hg hgt have h_second : eventCondExp P.μ S.neverTreatedEvent (fun ω => S.YofNT t ω - S.YofNT (S.predFin g hg) ω) = eventCondExp P.μ S.neverTreatedEvent (fun ω => S.factualY t ω - S.factualY (S.predFin g hg) ω) := by unfold eventCondExp rw [MeasureTheory.integral_congr_ae] rw [EventuallyEq, MeasureTheory.ae_restrict_iff' S.measurableSet_neverTreatedEvent] filter_upwards [S.factualY_eq_YofNT_on_NT hA t, S.factualY_eq_YofNT_on_NT hA (S.predFin g hg)] with ω ht hpred hω rw [ht hω, hpred hω] rw [hATT_split, h_first, h_pt, h_second]
13 supporting declarations (lemmas, instances)
DID 13 core · 6 supporting This file formalizes two-period difference-in-differences identification of the average treatment effect on the treated. ★ PODIDSystem★ att_did

Two-Period Difference-in-Differences

This file formalizes two-period difference-in-differences identification of the average treatment effect on the treated. It packages the treatment and outcome variables, the parallel-trends assumptions, and the resulting observable contrast.

The proof works at the event-conditional-mean level: it needs consistency, no anticipation, parallel trends, positivity of treated and control groups, and integrability of the counterfactual outcomes that enter the DID contrast. The main theorem att_did identifies the treated-group mean counterfactual contrast with the observed treated-minus-control difference in outcome changes.

structure PODIDSystem reviewed
Causalean.PO

A two-period DID system packages a treatment node whose value space is identified with the booleans, together with a pre-period outcome node and a post-period outcome node each of whose value spaces is identified with the real line; the treatment node is required to be distinct from the pre-period outcome node and distinct from the post-period outcome node.

Definition (Lean source)
P :
D :
P.V
Y₀ :
P.V
Y₁ :
P.V
hDbool :
P.X D ≃ᵐ Bool
hY0real :
P.X Y₀ ≃ᵐ ℝ
hY1real :
P.X Y₁ ≃ᵐ ℝ
hDY0 :
D ≠ Y₀
hDY1 :
D ≠ Y₁
Causalean.PO.PODIDSystem · Causalean/PO/ID/Exact/DID.lean:34 · uses POSystem
def dVar reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the binary treatment potential-outcome variable is its treatment node with values represented as false or true.

Definition (Lean source)
P :
shared
S :
shared
dVar S :
⟨S.D, S.hDbool⟩
def y0Var reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the real-valued pre-period outcome potential-outcome variable is its pre-period outcome node.

Definition (Lean source)
P :
shared
S :
shared
y0Var S :
POVar P ℝ
⟨S.Y₀, S.hY0real⟩
def y1Var reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the real-valued post-period outcome potential-outcome variable is its post-period outcome node.

Definition (Lean source)
P :
shared
S :
shared
y1Var S :
POVar P ℝ
⟨S.Y₁, S.hY1real⟩
def Y0ofD reviewed
Causalean.PO.PODIDSystem

For a two-period DID system and a binary treatment arm, the pre-period potential-outcome function gives each unit's pre-period outcome when treatment is fixed to that arm.

Definition (Lean source)
P :
shared
S :
shared
d :
Y0ofD S d :
P.Ω → ℝ
S.y0Var.cfUnder S.dVar d
Causalean.PO.PODIDSystem.Y0ofD · Causalean/PO/ID/Exact/DID.lean:66 · uses PODIDSystem , POSystem
def Y1ofD reviewed
Causalean.PO.PODIDSystem

For a two-period DID system and a binary treatment arm, the post-period potential-outcome function gives each unit's post-period outcome when treatment is fixed to that arm.

Definition (Lean source)
P :
shared
S :
shared
d :
Y1ofD S d :
P.Ω → ℝ
S.y1Var.cfUnder S.dVar d
Causalean.PO.PODIDSystem.Y1ofD · Causalean/PO/ID/Exact/DID.lean:71 · uses PODIDSystem , POSystem
def factualD reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the factual treatment function assigns each unit its observed binary treatment.

Definition (Lean source)
P :
shared
S :
shared
factualD S :
P.Ω → Bool
S.dVar.factual
Causalean.PO.PODIDSystem.factualD · Causalean/PO/ID/Exact/DID.lean:76 · uses PODIDSystem , POSystem
def factualY₀ reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the factual pre-period outcome function assigns each unit its observed pre-period outcome.

Definition (Lean source)
P :
shared
S :
shared
factualY₀ S :
P.Ω → ℝ
S.y0Var.factual
Causalean.PO.PODIDSystem.factualY₀ · Causalean/PO/ID/Exact/DID.lean:80 · uses PODIDSystem , POSystem
def factualY₁ reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the factual post-period outcome function assigns each unit its observed post-period outcome.

Definition (Lean source)
P :
shared
S :
shared
factualY₁ S :
P.Ω → ℝ
S.y1Var.factual
Causalean.PO.PODIDSystem.factualY₁ · Causalean/PO/ID/Exact/DID.lean:84 · uses PODIDSystem , POSystem
def dEvent reviewed
Causalean.PO.PODIDSystem

For a two-period DID system and a binary treatment arm, the treatment event is the set of units whose observed treatment equals that arm.

Definition (Lean source)
P :
shared
S :
shared
d :
dEvent S d :
Set P.Ω
S.dVar.event d
Causalean.PO.PODIDSystem.dEvent · Causalean/PO/ID/Exact/DID.lean:88 · uses PODIDSystem , POSystem
def ATT reviewed
Causalean.PO.PODIDSystem

For a two-period DID system, the average treatment effect on the treated is the mean, conditional on observed treatment, of the difference between each treated unit's post-period potential outcomes under treatment and no treatment.

Definition (Lean source)
P :
shared
S :
shared
ATT S :
eventCondExp P.μ (S.dEvent true) (fun ω => S.Y1ofD true ω - S.Y1ofD false ω)
Causalean.PO.PODIDSystem.ATT · Causalean/PO/ID/Exact/DID.lean:118 · uses PODIDSystem , POSystem
structure Assumptions reviewed
Causalean.PO.PODIDSystem

Assumptions for two-period difference-in-differences identification of the ATT (def:po-did-assumptions). In words: the observed outcomes coincide with the realized-arm potential outcomes; in the pre-period the treated and control groups have the same potential outcome regardless of treatment; and absent treatment the two groups would have changed in parallel between the two periods. The treated group and the control group each occur with positive probability, and the control pre-period outcome, the control post-period outcome, and the treated post-period outcome are integrable, so the group-conditional means are well-defined and finite.

Definition (Lean source)
P :
shared
S :
consistency :
P.Consistency

Consistency (SUTVA): the observed outcome equals the potential outcome of the realized treatment arm.

noAnticipation :
∀ᵐ ω ∂P.μ, S.Y0ofD true ω = S.Y0ofD false ω

No anticipation: in the pre-period the potential outcome does not depend on the (future) treatment, so Y₀(1) = Y₀(0) a.s.

parallelTrends :
eventCondExp P.μ (S.dEvent true) (fun ω => S.Y1ofD false ω - S.Y0ofD false ω)
= eventCondExp P.μ (S.dEvent false) (fun ω => S.Y1ofD false ω - S.Y0ofD false ω)

Parallel trends: the average untreated change from the pre- to the post-period is the same in the treated group as in the control group.

posTrue_ne_zero :
P.μ (S.dEvent true) ≠ 0

The treated group has positive probability, so its group-mean is defined. (Finiteness μ ≠ ⊤ is automatic: P.μ is a probability measure.)

posFalse_ne_zero :
P.μ (S.dEvent false) ≠ 0

The control group has positive probability, so its group-mean is defined.

intY0ofD_false :
Integrable (S.Y0ofD false) P.μ

Integrability of the control pre-period potential outcome Y₀(0).

intY1ofD_false :
Integrable (S.Y1ofD false) P.μ

Integrability of the control post-period potential outcome Y₁(0).

intY1ofD_true :
Integrable (S.Y1ofD true) P.μ

Integrability of the treated post-period potential outcome Y₁(1).

Causalean.PO.PODIDSystem.Assumptions · Causalean/PO/ID/Exact/DID.lean:124 · uses PODIDSystem , POSystem
theorem att_did reviewed
Causalean.PO.PODIDSystem

Under the two-period DID assumptions — consistency, no-anticipation, parallel trends, and positive-probability, integrable treatment and control groups, the average treatment effect on the treated equals the difference between the treated group's mean pre-to-post outcome change and the control group's mean pre-to-post outcome change.

Formal statement
P :
shared
S :
shared
hA :
S.Assumptions
S.ATT
= eventCondExp P.μ (S.dEvent true) (fun ω => S.factualY₁ ω - S.factualY₀ ω)
- eventCondExp P.μ (S.dEvent false) (fun ω => S.factualY₁ ω - S.factualY₀ ω)
Proof (Lean source)
theorem att_did (hA : S.Assumptions) : S.ATT = eventCondExp P.μ (S.dEvent true) (fun ω => S.factualY₁ ω - S.factualY₀ ω) - eventCondExp P.μ (S.dEvent false) (fun ω => S.factualY₁ ω - S.factualY₀ ω) := by -- Step 1: by no anticipation, `Y₁(1) - Y₁(0)` rewrites a.e. as -- `(Y₁(1) - Y₀(1)) - (Y₁(0) - Y₀(0))`. have hAE : (fun ω => S.Y1ofD true ω - S.Y1ofD false ω) =ᵐ[P.μ] fun ω => (S.Y1ofD true ω - S.Y0ofD true ω) - (S.Y1ofD false ω - S.Y0ofD false ω) := by refine hA.noAnticipation.mono (fun ω hω => ?_) change S.Y1ofD true ω - S.Y1ofD false ω = (S.Y1ofD true ω - S.Y0ofD true ω) - (S.Y1ofD false ω - S.Y0ofD false ω) rw [hω]; ring -- Step 2: split via additivity. Use the `eventCondExp` definition and -- `integral_congr_ae` + `integral_sub`. have hATT_split : S.ATT = eventCondExp P.μ (S.dEvent true) (fun ω => S.Y1ofD true ω - S.Y0ofD true ω) - eventCondExp P.μ (S.dEvent true) (fun ω => S.Y1ofD false ω - S.Y0ofD false ω) := by unfold ATT rw [eventCondExp_congr_ae P.μ (S.dEvent true) (ae_restrict_of_ae hAE)] -- `Y0ofD true` is integrable via a.e. equality with `Y0ofD false`. have hY0true_int : Integrable (S.Y0ofD true) P.μ := hA.intY0ofD_false.congr (hA.noAnticipation.mono (fun _ h => h.symm)) exact eventCondExp_sub P.μ (S.dEvent true) (hA.intY1ofD_true.sub hY0true_int).integrableOn (hA.intY1ofD_false.sub hA.intY0ofD_false).integrableOn -- Step 3: on `dEvent true`, consistency gives -- `Y₁(1) - Y₀(1) = factualY₁ - factualY₀`. have h_first : eventCondExp P.μ (S.dEvent true) (fun ω => S.Y1ofD true ω - S.Y0ofD true ω) = eventCondExp P.μ (S.dEvent true) (fun ω => S.factualY₁ ω - S.factualY₀ ω) := (eventCondExp_congr_on P.μ (S.measurableSet_dEvent true) (fun ω hω => (S.factualDiff_eq_cfDiff_on_dEvent hA.consistency true ω hω).symm)) -- Step 4: parallel trends rewrites the second term to condition on `D=0`. have h_pt : eventCondExp P.μ (S.dEvent true) (fun ω => S.Y1ofD false ω - S.Y0ofD false ω) = eventCondExp P.μ (S.dEvent false) (fun ω => S.Y1ofD false ω - S.Y0ofD false ω) := hA.parallelTrends -- Step 5: on `dEvent false`, consistency gives -- `Y₁(0) - Y₀(0) = factualY₁ - factualY₀`. have h_second : eventCondExp P.μ (S.dEvent false) (fun ω => S.Y1ofD false ω - S.Y0ofD false ω) = eventCondExp P.μ (S.dEvent false) (fun ω => S.factualY₁ ω - S.factualY₀ ω) := eventCondExp_congr_on P.μ (S.measurableSet_dEvent false) (fun ω hω => (S.factualDiff_eq_cfDiff_on_dEvent hA.consistency false ω hω).symm) rw [hATT_split, h_first, h_pt, h_second]
6 supporting declarations (lemmas, instances)
Frontdoor 24 core · 15 supporting This file formalizes classical frontdoor identification for a binary treatment, finite mediator, and real outcome in the potential-outcome framework. ★ POFrontdoorSystem★ EofY_eq_frontdoorTerm★ ate_frontdoor

Frontdoor Average Treatment Effect

This file formalizes classical frontdoor identification for a binary treatment, finite mediator, and real outcome in the potential-outcome framework. It defines the frontdoor subsystem, assumptions, observable adjustment functional, and the proof equating that functional with the average treatment effect.

The proof uses event-conditional means, full mediation, two exchangeability assumptions, and composition consistency to relate the two-variable counterfactual outcome through the mediator to the single-treatment potential outcome.

structure POFrontdoorSystem reviewed
Causalean.PO

A frontdoor system packages, within an ambient potential-outcome system, a binary treatment A, a finite discrete mediator M valued in a finite type, and a real-valued outcome Y, where the treatment, mediator, and outcome are pairwise distinct variables.

Definition (Lean source)
A :
P.V
M :
P.V
Y :
P.V
hAbool :
P.X A ≃ᵐ Bool
hMequiv :
P.X M ≃ᵐ β
hYreal :
P.X Y ≃ᵐ ℝ
hAM :
A ≠ M
hAY :
A ≠ Y
hMY :
M ≠ Y
Causalean.PO.POFrontdoorSystem · Causalean/PO/ID/Exact/Frontdoor.lean:49 · uses POSystem
def aVar reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the binary treatment potential-outcome variable is its treatment node equipped with its binary value representation.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
aVar S :
⟨S.A, S.hAbool⟩
def mVar reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the mediator potential-outcome variable is its mediator node equipped with its finite mediator-value representation.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
mVar S :
POVar P β
⟨S.M, S.hMequiv⟩
def yVar reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the real-valued outcome potential-outcome variable is its outcome node equipped with its real-valued representation.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
yVar S :
POVar P ℝ
⟨S.Y, S.hYreal⟩
def YofA reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a treatment arm, the potential outcome assigns to each unit the real outcome it would have under that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
YofA S a :
P.Ω → ℝ
S.yVar.cfUnder S.aVar a
Causalean.PO.POFrontdoorSystem.YofA · Causalean/PO/ID/Exact/Frontdoor.lean:83 · uses POFrontdoorSystem , POSystem
def MofA reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a treatment arm, the potential mediator assigns to each unit the mediator value it would have under that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
MofA S a :
P.Ω → β
S.mVar.cfUnder S.aVar a
Causalean.PO.POFrontdoorSystem.MofA · Causalean/PO/ID/Exact/Frontdoor.lean:86 · uses POFrontdoorSystem , POSystem
def regimeAM reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, a treatment arm, and a mediator value, the joint treatment--mediator intervention regime fixes treatment and mediator simultaneously.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
m :
β
regimeAM S a m :
Regime P.V P.X
(Regime.single S.A (S.hAbool.symm a)).sqcup (Regime.single S.M (S.hMequiv.symm m)) (Regime.single_disjoint_single S.hAM _ _)
Causalean.PO.POFrontdoorSystem.regimeAM · Causalean/PO/ID/Exact/Frontdoor.lean:89 · uses POFrontdoorSystem , POSystem , Regime
def YofAM reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, a treatment arm, and a mediator value, the joint potential outcome assigns to each unit the outcome under simultaneously fixing treatment and mediator to those values.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
m :
β
YofAM S a m :
P.Ω → ℝ
S.yVar.cf (S.regimeAM a m)
Causalean.PO.POFrontdoorSystem.YofAM · Causalean/PO/ID/Exact/Frontdoor.lean:98 · uses POFrontdoorSystem , POSystem
def factualA reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the factual treatment assigns each unit its observed binary treatment.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
factualA S :
P.Ω → Bool
S.aVar.factual
Causalean.PO.POFrontdoorSystem.factualA · Causalean/PO/ID/Exact/Frontdoor.lean:104 · uses POFrontdoorSystem , POSystem
def factualM reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the factual mediator assigns each unit its observed mediator value.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
factualM S :
P.Ω → β
S.mVar.factual
Causalean.PO.POFrontdoorSystem.factualM · Causalean/PO/ID/Exact/Frontdoor.lean:106 · uses POFrontdoorSystem , POSystem
def factualY reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the factual outcome assigns each unit its observed real outcome.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
factualY S :
P.Ω → ℝ
S.yVar.factual
Causalean.PO.POFrontdoorSystem.factualY · Causalean/PO/ID/Exact/Frontdoor.lean:108 · uses POFrontdoorSystem , POSystem
def aEvent reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a treatment arm, the treatment event is the set of units whose observed treatment equals that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
aEvent S a :
Set P.Ω
S.aVar.event a
Causalean.PO.POFrontdoorSystem.aEvent · Causalean/PO/ID/Exact/Frontdoor.lean:137 · uses POFrontdoorSystem , POSystem
def mEvent reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a mediator value, the mediator event is the set of units whose observed mediator equals that value.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
m :
β
mEvent S m :
Set P.Ω
S.mVar.event m
Causalean.PO.POFrontdoorSystem.mEvent · Causalean/PO/ID/Exact/Frontdoor.lean:139 · uses POFrontdoorSystem , POSystem
def mUnderA reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a treatment arm, the mediator under that treatment regime is the mediator potential outcome represented together with the intervention that fixes treatment to that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
mUnderA S a :
⟨S.mVar, Regime.single S.A (S.hAbool.symm a)⟩
def mBundle reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the counterfactual mediator bundle consists of the mediator potential outcomes under treatment and control.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
mBundle S :
POCFBundle.cons (S.mUnderA true) <| POCFBundle.cons (S.mUnderA false) <| POCFBundle.nil P
def pA reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a treatment arm, the treatment-arm probability is the probability that the observed treatment equals that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
pA S a :
(P.μ (S.aEvent a)).toReal
def pMgivenA reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, a mediator value, and a treatment arm, the conditional mediator probability is the event-conditional probability that the observed mediator equals that value given that observed treatment equals that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
m :
β
a :
pMgivenA S m a :
eventCondExp P.μ (S.aEvent a) (S.mVar.indicator m)
Causalean.PO.POFrontdoorSystem.pMgivenA · Causalean/PO/ID/Exact/Frontdoor.lean:169 · uses POFrontdoorSystem , POSystem
def EYgivenAM reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, a treatment arm, and a mediator value, the conditional outcome mean is the event-conditional mean of the observed outcome among units with that observed treatment and mediator value.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
m :
β
EYgivenAM S a m :
eventCondExp P.μ (S.aEvent a ∩ S.mEvent m) S.factualY
Causalean.PO.POFrontdoorSystem.EYgivenAM · Causalean/PO/ID/Exact/Frontdoor.lean:173 · uses POFrontdoorSystem , POSystem
def frontdoorTerm reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system and a treatment arm, the frontdoor-adjusted functional is the finite sum over mediator values of the treatment-probability-weighted conditional outcome means, weighted by the mediator distribution conditional on that arm.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
a :
frontdoorTerm S a :
∑ m : β, (S.EYgivenAM true m * S.pA true + S.EYgivenAM false m * S.pA false) * S.pMgivenA m a
Causalean.PO.POFrontdoorSystem.frontdoorTerm · Causalean/PO/ID/Exact/Frontdoor.lean:177 · uses POFrontdoorSystem , POSystem
def ATE reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the average treatment effect is the population mean of the difference between each unit's potential outcome under treatment and under control.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
ATE S :
∫ ω, S.YofA true ω - S.YofA false ω ∂P.μ
def frontdoorATE reviewed
Causalean.PO.POFrontdoorSystem

For a frontdoor system, the observable frontdoor-adjusted average treatment effect is the frontdoor-adjusted functional under treatment minus that under control.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
S :
shared
frontdoorATE S :
S.frontdoorTerm true - S.frontdoorTerm false
Causalean.PO.POFrontdoorSystem.frontdoorATE · Causalean/PO/ID/Exact/Frontdoor.lean:188 · uses POFrontdoorSystem , POSystem
structure Assumptions reviewed
Causalean.PO.POFrontdoorSystem

Frontdoor identifying assumptions. Bundles, for a frontdoor system, consistency of the underlying potential-outcome system, the full-mediation exclusion restriction that the two-treatment-and-mediator outcome does not depend on the treatment arm, treatment–mediator exchangeability, mediator–outcome exchangeability within treatment arms, positivity of each treatment arm, positivity of the mediator within the support of its counterfactual under a treatment arm, cross-world independence of the counterfactual mediator from the full-mediation outcome, and integrability of the treatment-arm and joint treatment–mediator potential outcomes.

Definition (Lean source)
P :
shared
β :
Type u_1
shared
consistency :
P.Consistency

Consistency axiom for the ambient PO system.

fullMediation :
∀ (a a' : Bool) (m : β), S.YofAM a m =ᵐ[P.μ] S.YofAM a' m

Full mediation / exclusion restriction: Y(a,m) = Y(a',m) a.s. for all a, a' ∈ {0,1} and m ∈ β.

exch_AM :
P.IndepCF (RegimedVar.ofFactual S.aVar) S.mBundle P.μ

Treatment–mediator exchangeability: A ⊥ (M(1), M(0)). Equivalent (for binary A) to M(a) ⊥ A for each a.

exch_MY :
∀ (a : Bool) (m : β)
if
0 < P.μ ({ω | S.MofA a ω = m})
then
∀ a' : Bool,
eventCondExp P.μ (S.aEvent a' ∩ S.mEvent m) (S.YofAM true m)
= eventCondExp P.μ (S.aEvent a') (S.YofAM true m)

Mediator–outcome exchangeability within treatment arms: for mediator values in the support of M(a), and each treatment arm a', the conditional law of Y(m) (= any Y(a,m) by full mediation) on {A = a'} ∩ {M = m} equals its conditional law on {A = a'}. Stated at the eventCondExp level (discrete form, matching Manski/LATE style), and gated by positive M(a) mass so zero-probability mediator cells need no exchangeability assumption.

posA :
∀ a : Bool, 0 < P.μ (S.aEvent a)

Positivity (treatment): P(A = a) > 0.

posAM :
∀ (a : Bool) (m : β)
if
0 < P.μ ({ω | S.MofA a ω = m})
then
∀ a' : Bool, 0 < P.μ (S.aEvent a' ∩ S.mEvent m)

Positivity (mediator within support of M(a)): if P(M(a) = m) > 0, then for every treatment arm a' we have P(A=a', M=m) > 0. Stated on the ENNReal-valued measure for convenience.

indep_Y_M :
∀ (a : Bool) (m : β), IndepFun (S.MofA a) (S.YofAM true m) P.μ

Joint mediator–outcome independence across worlds: M(a) ⊥ Y(1, m) as IndepFun. This is required for the drop-of-conditioning step

E[Y(m) · 1_{M(a)=m}] = E[Y(m)] · P(M(a) = m)

used in the frontdoor proof sketch. It is not derivable from the other four assumptions in the bare PO framework: under a graphical frontdoor DAG it would follow from d-separation (no directed path from the counterfactual mediator M(a) to the full-mediation outcome Y(1, m)), but in the bare PO setting it must be stated explicitly.

Cross-world independence M(a) ⟂ Y(1, m). In Pearl's graphical frontdoor this follows from d-separation; here we state it directly as a primitive PO assumption. A future graphical-derivation file under SCM/ID/ could derive this from the three Pearl frontdoor graph conditions via the SWIG/d-separation infrastructure in Causalean/Graph/.

integrable_YofA :
∀ a : Bool, Integrable (S.YofA a) P.μ

Integrability of each Y(a).

integrable_YofAM :
∀ (a : Bool) (m : β), Integrable (S.YofAM a m) P.μ

Integrability of each Y(a,m).

Causalean.PO.POFrontdoorSystem.Assumptions · Causalean/PO/ID/Exact/Frontdoor.lean:193 · uses POFrontdoorSystem , POSystem
theorem EofY_eq_frontdoorTerm reviewed
Causalean.PO.POFrontdoorSystem

Frontdoor identification (individual regime). Under the frontdoor identifying assumption bundle, for each treatment arm a, the mean potential outcome under arm a equals the frontdoor functional frontdoorTerm(a), built from the mediator distribution given a and the outcome regression on mediator and treatment.

Formal statement
P :
shared
β :
Type u_1
shared
S :
shared
hA :
S.Assumptions
a :
∫ ω, S.YofA a ω ∂P.μ = S.frontdoorTerm a
Proof (Lean source)
theorem EofY_eq_frontdoorTerm (hA : S.Assumptions) (a : Bool) : ∫ ω, S.YofA a ω ∂P.μ = S.frontdoorTerm a := by -- Shorthands. set mSet : β → Set P.Ω := fun m => {ω | S.MofA a ω = m} with hmSet_def have hmSet_meas : ∀ m, MeasurableSet (mSet m) := fun m => S.measurable_MofA a (MeasurableSet.singleton m) have hpA_ne_top : P.μ (S.aEvent a) ≠ ⊤ := measure_ne_top _ _ have hpA_ne_zero : P.μ (S.aEvent a) ≠ 0 := (hA.posA a).ne' have hpA_toReal_pos : 0 < (P.μ (S.aEvent a)).toReal := by rw [ENNReal.toReal_pos_iff]; exact ⟨hA.posA a, lt_top_iff_ne_top.mpr hpA_ne_top⟩ have hpA_toReal_ne_zero : (P.μ (S.aEvent a)).toReal ≠ 0 := hpA_toReal_pos.ne' -- ─────────────────────────────────────────────────────────────────────────── -- (A) Mediator-marginal identity: μ(mSet m).toReal = pMgivenA m a. -- ─────────────────────────────────────────────────────────────────────────── -- (A.1) Independence: factualA ⊥ MofA a (from exch_AM component projection). have hInd_AMa : IndepFun S.factualA (S.MofA a) P.μ := by cases a with | true => exact hA.exch_AM.component (0 : Fin 2) | false => exact hA.exch_AM.component (1 : Fin 2) -- (A.2) Independence on preimage sets: μ(aEvent a ∩ mSet m) = μ(aEvent a) * μ(mSet m). have hIndepMeas : ∀ m, P.μ (S.aEvent a ∩ mSet m) = P.μ (S.aEvent a) * P.μ (mSet m) := by intro m have h := hInd_AMa.measure_inter_preimage_eq_mul (s := {a}) (t := {m}) (measurableSet_singleton _) (measurableSet_singleton _) -- `aEvent a = factualA ⁻¹' {a}` and `mSet m = MofA a ⁻¹' {m}` both by rfl. exact h -- (A.3) Consistency set identity: aEvent a ∩ mSet m = aEvent a ∩ mEvent m. have hConsist_set : ∀ m, S.aEvent a ∩ mSet m = S.aEvent a ∩ S.mEvent m := by intro m ext ω refine ⟨?_, ?_⟩ · rintro ⟨hA_ω, hMofA_ω⟩ refine ⟨hA_ω, ?_⟩ have h_eq := MofA_eq_factualM_on_aEvent hA.consistency a hA_ω change S.factualM ω = m rw [← h_eq]; exact hMofA_ω · rintro ⟨hA_ω, hM_ω⟩ refine ⟨hA_ω, ?_⟩ have h_eq := MofA_eq_factualM_on_aEvent hA.consistency a hA_ω change S.MofA a ω = m rw [h_eq]; exact hM_ω -- (A.4) indM m equals set indicator of mEvent m. have hIndM : ∀ m, S.mVar.indicator m = (S.mEvent m).indicator (fun _ => (1:ℝ)) := fun m => S.mVar.indicator_eq_event_indicator m -- (A.5) Evaluate pMgivenA m a in closed form. have hpM_val : ∀ m, S.pMgivenA m a = (P.μ (S.aEvent a ∩ S.mEvent m)).toReal / (P.μ (S.aEvent a)).toReal := by intro m unfold pMgivenA eventCondExp rw [hIndM] rw [MeasureTheory.setIntegral_indicator (S.measurableSet_mEvent m)] rw [MeasureTheory.setIntegral_one_eq_measureReal] rfl -- (A.6) Mediator-marginal identity. have hMarginal : ∀ m, (P.μ (mSet m)).toReal = S.pMgivenA m a := by intro m rw [hpM_val m] have h₁ : (P.μ (S.aEvent a ∩ mSet m)).toReal = (P.μ (S.aEvent a)).toReal * (P.μ (mSet m)).toReal := by rw [hIndepMeas m] exact ENNReal.toReal_mul have h₂ : (P.μ (S.aEvent a ∩ S.mEvent m)).toReal = (P.μ (S.aEvent a)).toReal * (P.μ (mSet m)).toReal := by rw [← hConsist_set m]; exact h₁ rw [h₂] field_simp -- ─────────────────────────────────────────────────────────────────────────── -- (D) Inner integral: ∫ YofAM true m = ∑ a', EYgivenAM a' m · pA a'. -- ─────────────────────────────────────────────────────────────────────────── have hInner : ∀ m : β, 0 < P.μ (mSet m) → ∫ ω, S.YofAM true m ω ∂P.μ = ∑ a' : Bool, S.EYgivenAM a' m * S.pA a' := by intro m hm_pos -- Tower over Bool partition by A. rw [integral_eq_sum_eventCondExp_aEvent (S := S) _ (hA.integrable_YofAM true m)] refine Finset.sum_congr rfl (fun a' _ => ?_) -- Use exch_MY to pass to aEvent a' ∩ mEvent m. rw [← hA.exch_MY a m hm_pos a'] -- Inside the event aEvent a' ∩ mEvent m, YofAM true m = factualY a.e. -- First, full mediation: YofAM true m =ᵐ[μ] YofAM a' m. -- Then, consistency on aEvent a' ∩ mEvent m: YofAM a' m = factualY. have hYeq : ∀ ω ∈ S.aEvent a' ∩ S.mEvent m, S.YofAM a' m ω = S.factualY ω := fun ω hω => YofAM_eq_factualY_on_aMEvent hA.consistency a' m hω -- eventCondExp (aEvent a' ∩ mEvent m) (YofAM true m) -- = eventCondExp (aEvent a' ∩ mEvent m) (YofAM a' m) [full mediation a.e.] -- = eventCondExp (aEvent a' ∩ mEvent m) factualY [consistency on event] have hcongr_ae : eventCondExp P.μ (S.aEvent a' ∩ S.mEvent m) (S.YofAM true m) = eventCondExp P.μ (S.aEvent a' ∩ S.mEvent m) (S.YofAM a' m) := by unfold eventCondExp congr 1 refine MeasureTheory.integral_congr_ae ?_ exact (Filter.EventuallyEq.filter_mono (hA.fullMediation true a' m) MeasureTheory.ae_restrict_le) have hcongr_event : eventCondExp P.μ (S.aEvent a' ∩ S.mEvent m) (S.YofAM a' m) = eventCondExp P.μ (S.aEvent a' ∩ S.mEvent m) S.factualY := by unfold eventCondExp congr 1 refine MeasureTheory.setIntegral_congr_fun ((S.measurableSet_aEvent a').inter (S.measurableSet_mEvent m)) ?_ exact hYeq rw [hcongr_ae, hcongr_event] -- Now the goal is EYgivenAM a' m * pA a' = eventCondExp ... factualY * μ(aEvent a').toReal. unfold EYgivenAM pA ring -- ─────────────────────────────────────────────────────────────────────────── -- (B,C) ∫ YofA a = ∑ m, (∫ YofAM true m) · μ(mSet m).toReal. -- Uses composition + full mediation on the slice {MofA a = m}, and drop of -- conditioning from exch_AM. -- ─────────────────────────────────────────────────────────────────────────── have hOuter : ∀ m : β, ∫ ω in mSet m, S.YofA a ω ∂P.μ = (P.μ (mSet m)).toReal * ∫ ω, S.YofAM true m ω ∂P.μ := by intro m -- Step (B): on mSet m, YofA a = YofAM a m (composition), and -- YofAM a m =ᵐ YofAM true m (full mediation), so on mSet m, -- YofA a = YofAM true m a.e. (viewing full mediation as an a.e. equality -- of the full functions, which restricts to mSet m). have hB : ∫ ω in mSet m, S.YofA a ω ∂P.μ = ∫ ω in mSet m, S.YofAM true m ω ∂P.μ := by -- Use a.e. equality on mSet m: YofA a =ᵐ[μ.restrict (mSet m)] YofAM true m. refine MeasureTheory.integral_congr_ae ?_ -- On mSet m (a pointwise event): YofA a = YofAM a m. -- Off mSet m we need nothing, but we produce a restrict-a.e. statement via -- indicator/filter reasoning. Simplest: combine pointwise composition -- identity (on mSet m) with a.e. full mediation, restricted. have h_comp_on : ∀ ω ∈ mSet m, S.YofA a ω = S.YofAM a m ω := by intro ω hω exact (YofAM_eq_YofA_on_MofA_event hA.consistency a m hω).symm -- YofAM a m =ᵐ[μ] YofAM true m. have h_fm := (hA.fullMediation a true m).symm -- YofAM true m =ᵐ YofAM a m -- Combine: for almost every ω in mSet m, YofA a ω = YofAM true m ω. have h_fm_restrict : S.YofAM a m =ᵐ[P.μ.restrict (mSet m)] S.YofAM true m := by exact (hA.fullMediation a true m).filter_mono MeasureTheory.ae_restrict_le -- YofA a =ᵐ[restrict] YofAM a m (pointwise on mSet m ⇒ a.e. on restrict). have h_comp_ae : S.YofA a =ᵐ[P.μ.restrict (mSet m)] S.YofAM a m := by rw [EventuallyEq, MeasureTheory.ae_restrict_iff' (hmSet_meas m)] filter_upwards with ω hω using h_comp_on ω hω exact h_comp_ae.trans h_fm_restrict rw [hB] -- Step (C): drop-of-conditioning for YofAM true m using indep_Y_M. -- mSet m = (MofA a) ⁻¹' {m}, so IndepFun gives the preimage integral identity. have hdrop : ∫ ω in (S.MofA a) ⁻¹' {m}, id (S.YofAM true m ω) ∂P.μ = (P.μ ((S.MofA a) ⁻¹' {m})).toReal * ∫ ω, id (S.YofAM true m ω) ∂P.μ := (hA.indep_Y_M a m).integral_restrict_preimage_eq_mul (S.measurable_MofA a).aemeasurable (S.measurable_YofAM true m).aemeasurable (measurableSet_singleton m) ((S.measurable_MofA a) (measurableSet_singleton m)) measurable_id.aestronglyMeasurable have hpre : mSet m = (S.MofA a) ⁻¹' {m} := rfl rw [hpre] exact hdrop -- ─────────────────────────────────────────────────────────────────────────── -- Main chain: combine (i) partition, (B,C) drop + marginal, (D) inner. -- ─────────────────────────────────────────────────────────────────────────── rw [integral_eq_sum_integral_MofA (S := S) _ (hA.integrable_YofA a) a] -- Now the goal is ∑ m, ∫ in {MofA a = m}, YofA a = frontdoorTerm a. -- Rewrite the LHS sum using hOuter, hMarginal, hInner. have hStep : ∀ m : β, ∫ ω in mSet m, S.YofA a ω ∂P.μ = S.pMgivenA m a * ∑ a' : Bool, S.EYgivenAM a' m * S.pA a' := by intro m by_cases hm_pos : 0 < P.μ (mSet m) · rw [hOuter m, hInner m hm_pos, hMarginal m] · have hm_zero : P.μ (mSet m) = 0 := le_antisymm (not_lt.mp hm_pos) bot_le rw [hOuter m, ← hMarginal m, hm_zero] simp have hLHS : ∑ m : β, ∫ ω in mSet m, S.YofA a ω ∂P.μ = ∑ m : β, S.pMgivenA m a * ∑ a' : Bool, S.EYgivenAM a' m * S.pA a' := Finset.sum_congr rfl (fun m _ => hStep m) rw [hLHS] -- Remaining: ∑ m, pMgivenA m a * (∑ a', EYgivenAM a' m * pA a') = frontdoorTerm a. unfold frontdoorTerm refine Finset.sum_congr rfl (fun m _ => ?_) -- pMgivenA m a * (EYgivenAM true m * pA true + EYgivenAM false m * pA false) -- = (EYgivenAM true m * pA true + EYgivenAM false m * pA false) * pMgivenA m a. rw [Fintype.sum_bool] ring
theorem ate_frontdoor reviewed
Causalean.PO.POFrontdoorSystem

Frontdoor identification of the ATE. Under the frontdoor identifying assumption bundle, the average treatment effect equals the frontdoor estimand frontdoorATE, the difference of the frontdoor functional evaluated at the two treatment arms.

Formal statement
P :
shared
β :
Type u_1
shared
S :
shared
hA :
S.Assumptions
S.ATE = S.frontdoorATE
Proof (Lean source)
theorem ate_frontdoor (hA : S.Assumptions) : S.ATE = S.frontdoorATE := by unfold ATE frontdoorATE rw [integral_sub (hA.integrable_YofA true) (hA.integrable_YofA false)] rw [EofY_eq_frontdoorTerm S hA true, EofY_eq_frontdoorTerm S hA false]
15 supporting declarations (lemmas, instances)
  • measurable_YofA lemma — Treatment-arm potential outcomes are measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    a :
    Measurable (S.YofA a)
    Proof (Lean source)
    @[fun_prop] lemma measurable_YofA (a : Bool) : Measurable (S.YofA a) := S.yVar.measurable_cfUnder S.aVar a
    Causalean.PO.POFrontdoorSystem.measurable_YofA · Causalean/PO/ID/Exact/Frontdoor.lean:113
  • measurable_MofA lemma — Treatment-arm potential mediators are measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    a :
    Measurable (S.MofA a)
    Proof (Lean source)
    @[fun_prop] lemma measurable_MofA (a : Bool) : Measurable (S.MofA a) := S.mVar.measurable_cfUnder S.aVar a
    Causalean.PO.POFrontdoorSystem.measurable_MofA · Causalean/PO/ID/Exact/Frontdoor.lean:117
  • measurable_YofAM lemma — Joint treatment-mediator potential outcomes are measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    a :
    m :
    β
    Measurable (S.YofAM a m)
    Proof (Lean source)
    @[fun_prop] lemma measurable_YofAM (a : Bool) (m : β) : Measurable (S.YofAM a m) := S.yVar.measurable_cf _
    Causalean.PO.POFrontdoorSystem.measurable_YofAM · Causalean/PO/ID/Exact/Frontdoor.lean:121
  • measurable_factualA lemma — The observed treatment is measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualA
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualA : Measurable S.factualA := S.aVar.measurable_factual
    Causalean.PO.POFrontdoorSystem.measurable_factualA · Causalean/PO/ID/Exact/Frontdoor.lean:125
  • measurable_factualM lemma — The observed mediator is measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualM
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualM : Measurable S.factualM := S.mVar.measurable_factual
    Causalean.PO.POFrontdoorSystem.measurable_factualM · Causalean/PO/ID/Exact/Frontdoor.lean:128
  • measurable_factualY lemma — The observed outcome is measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    Measurable S.factualY
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualY : Measurable S.factualY := S.yVar.measurable_factual
    Causalean.PO.POFrontdoorSystem.measurable_factualY · Causalean/PO/ID/Exact/Frontdoor.lean:131
  • measurableSet_aEvent lemma — The factual treatment event for a treatment arm is measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    a :
    MeasurableSet (S.aEvent a)
    Proof (Lean source)
    lemma measurableSet_aEvent (a : Bool) : MeasurableSet (S.aEvent a) := S.aVar.measurableSet_event _ (measurableSet_singleton _)
    Causalean.PO.POFrontdoorSystem.measurableSet_aEvent · Causalean/PO/ID/Exact/Frontdoor.lean:142
  • measurableSet_mEvent lemma — The factual mediator event for a mediator value is measurable.
    P :
    shared
    β :
    Type u_1
    shared
    S :
    shared
    m :
    β
    MeasurableSet (S.mEvent m)
    Proof (Lean source)
    lemma measurableSet_mEvent (m : β) : MeasurableSet (S.mEvent m) := S.mVar.measurableSet_event _ (measurableSet_singleton _)
    Causalean.PO.POFrontdoorSystem.measurableSet_mEvent · Causalean/PO/ID/Exact/Frontdoor.lean:145
  • MofA_eq_factualM_on_aEvent lemma — On the event {A = a}, M(a)(ω) = factualM ω. Single-target consistency.
    P :
    shared
    β :
    Type u_1
    shared
    hC :
    P.Consistency
    a :
    ω :
    P.Ω
    :
    ω ∈ S.aEvent a
    S.MofA a ω = S.factualM ω
    Proof (Lean source)
    lemma MofA_eq_factualM_on_aEvent (hC : P.Consistency) (a : Bool) {ω : P.Ω} (hω : ω ∈ S.aEvent a) : S.MofA a ω = S.factualM ω := POVar.cf_eq_factual_on_event hC S.mVar S.aVar a (Ne.symm S.hAM) hω
    Causalean.PO.POFrontdoorSystem.MofA_eq_factualM_on_aEvent · Causalean/PO/ID/Exact/Frontdoor.lean:261
  • YofAM_eq_factualY_on_aMEvent lemma — On the event {A = a} ∩ {M = m}, Y(a,m)(ω) = factualY ω. Multi-target consistency via cf_eq_factual_of_factualAgrees.
    P :
    shared
    β :
    Type u_1
    shared
    hC :
    P.Consistency
    a :
    m :
    β
    ω :
    P.Ω
    :
    ω ∈ S.aEvent a ∩ S.mEvent m
    S.YofAM a m ω = S.factualY ω
    Proof (Lean source)
    lemma YofAM_eq_factualY_on_aMEvent (hC : P.Consistency) (a : Bool) (m : β) {ω : P.Ω} (hω : ω ∈ S.aEvent a ∩ S.mEvent m) : S.YofAM a m ω = S.factualY ω := by -- The target set of `regimeAM a m` is `{A, M}`; `Y ∉ {A, M}` since `hAY, hMY`. have h_notmem : S.yVar.v ∉ (S.regimeAM a m).target := by simp only [regimeAM, Regime.sqcup_target, Regime.single_target, Finset.singleton_union, yVar, Finset.mem_insert, mem_singleton, not_or] exact ⟨S.hAY.symm, S.hMY.symm⟩ -- On `{A=a} ∩ {M=m}`, `ω` factually agrees with `regimeAM a m`, by combining -- the per-variable factual equalities `aVar.factual ω = a`, `mVar.factual ω = m`. have hAgrees : P.FactualAgrees (S.regimeAM a m) ω := POSystem.factualAgrees_sqcup _ (S.aVar.factualAgrees_single a hω.1) (S.mVar.factualAgrees_single m hω.2) exact POVar.cf_eq_factual_of_factualAgrees hC S.yVar (S.regimeAM a m) h_notmem ω hAgrees
    Causalean.PO.POFrontdoorSystem.YofAM_eq_factualY_on_aMEvent · Causalean/PO/ID/Exact/Frontdoor.lean:267
  • integrable_factualY_of_consistency_integrable_YofAM lemma — The observed outcome is integrable when all joint treatment-mediator potential outcomes are integrable and consistency holds.
    P :
    shared
    β :
    Type u_1
    shared
    hC :
    P.Consistency
    hY :
    ∀ (a : Bool) (m : β), Integrable (S.YofAM a m) P.μ
    Integrable S.factualY P.μ
    Proof (Lean source)
    lemma integrable_factualY_of_consistency_integrable_YofAM (hC : P.Consistency) (hY : ∀ (a : Bool) (m : β), Integrable (S.YofAM a m) P.μ) : Integrable S.factualY P.μ := by let cell : Bool → β → P.Ω → ℝ := fun a m ω => S.YofAM a m ω * S.aVar.indicator a ω * S.mVar.indicator m ω have hcell_int : ∀ a m, Integrable (cell a m) P.μ := by intro a m have hA_int : Integrable (fun ω => S.YofAM a m ω * S.aVar.indicator a ω) P.μ := S.aVar.integrable_mul_indicator a (measurableSet_singleton a) (hY a m) simpa [cell, mul_assoc] using S.mVar.integrable_mul_indicator m (measurableSet_singleton m) hA_int have hsum_int : Integrable (fun ω => ∑ a : Bool, ∑ m : β, cell a m ω) P.μ := by have hsum_beta : ∀ a, Integrable (fun ω => ∑ m : β, cell a m ω) P.μ := by intro a have hsum_finset : ∀ s : Finset β, Integrable (fun ω => s.sum fun m => cell a m ω) P.μ := by intro s refine Finset.induction_on s ?base ?step · simp · intro m s hms hs simp only [Finset.sum_insert hms] exact (hcell_int a m).add hs simpa using hsum_finset Finset.univ have htrue : Integrable (fun ω => ∑ m : β, cell true m ω) P.μ := hsum_beta true have hfalse : Integrable (fun ω => ∑ m : β, cell false m ω) P.μ := hsum_beta false simp only [Fintype.sum_bool] exact htrue.add hfalse refine hsum_int.congr (Filter.Eventually.of_forall ?_) intro ω have hA_indicator : ∀ a, S.aVar.indicator a ω = if S.factualA ω = a then 1 else 0 := by intro a by_cases hωa : S.factualA ω = a · simp [S.aVar.indicator_apply_eq_one hωa, hωa] · simp [S.aVar.indicator_apply_eq_zero hωa, hωa] have hM_indicator : ∀ m, S.mVar.indicator m ω = if S.factualM ω = m then 1 else 0 := by intro m by_cases hωm : S.factualM ω = m · simp [S.mVar.indicator_apply_eq_one hωm, hωm] · simp [S.mVar.indicator_apply_eq_zero hωm, hωm] change (∑ a : Bool, ∑ m : β, cell a m ω) = S.factualY ω rw [Fintype.sum_bool] cases hAω : S.factualA ω · simp only [hA_indicator, hAω, Bool.false_eq_true, ↓reduceIte, mul_zero, hM_indicator, mul_ite, mul_one, ite_self, Finset.sum_const_zero, Finset.sum_ite_eq, Finset.mem_univ, zero_add, cell] exact YofAM_eq_factualY_on_aMEvent hC false (S.factualM ω) (show ω ∈ S.aEvent false ∩ S.mEvent (S.factualM ω) from ⟨hAω, rfl⟩) · simp only [hA_indicator, hAω, ↓reduceIte, mul_one, hM_indicator, mul_ite, mul_zero, Finset.sum_ite_eq, Finset.mem_univ, Bool.true_eq_false, ite_self, Finset.sum_const_zero, add_zero, cell] exact YofAM_eq_factualY_on_aMEvent hC true (S.factualM ω) (show ω ∈ S.aEvent true ∩ S.mEvent (S.factualM ω) from ⟨hAω, rfl⟩)
    Causalean.PO.POFrontdoorSystem.integrable_factualY_of_consistency_integrable_YofAM · Causalean/PO/ID/Exact/Frontdoor.lean:286
  • integrable_factualY lemma — Compatibility projection for older call sites: factual outcome integrability is derived from consistency plus integrability of the finite Y(a,m) cells.
    P :
    shared
    β :
    Type u_1
    shared
    hA :
    S.Assumptions
    Integrable S.factualY P.μ
    Proof (Lean source)
    @[fun_prop] lemma integrable_factualY (hA : S.Assumptions) : Integrable S.factualY P.μ := S.integrable_factualY_of_consistency_integrable_YofAM hA.consistency hA.integrable_YofAM
    Causalean.PO.POFrontdoorSystem.Assumptions.integrable_factualY · Causalean/PO/ID/Exact/Frontdoor.lean:346
  • YofAM_eq_YofA_on_MofA_event lemma — Composition lemma (def:po-consistency, composition clause): on the event {M(a) = m}, Y(a, m)(ω) = Y(a)(ω).
    P :
    shared
    β :
    Type u_1
    shared
    hC :
    P.Consistency
    a :
    m :
    β
    ω :
    P.Ω
    :
    S.MofA a ω = m
    S.YofAM a m ω = S.YofA a ω
    Proof (Lean source)
    lemma YofAM_eq_YofA_on_MofA_event (hC : P.Consistency) (a : Bool) (m : β) {ω : P.Ω} (hω : S.MofA a ω = m) : S.YofAM a m ω = S.YofA a ω := by -- Disjointness of the two single-target regimes. have hdisj : (Regime.single S.A (S.hAbool.symm a)).Disjoint (Regime.single S.M (S.hMequiv.symm m)) := Regime.single_disjoint_single S.hAM _ _ -- `Y ∉ {A} ∪ {M}`. have hY_notmem : _root_.Disjoint ({S.Y} : Finset P.V) ((Regime.single S.A (S.hAbool.symm a)).target ∪ (Regime.single S.M (S.hMequiv.symm m)).target) := by simp only [Regime.single_target, Finset.singleton_union, Finset.disjoint_singleton_left, Finset.mem_insert, mem_singleton, not_or] exact ⟨fun h => S.hAY h.symm, fun h => S.hMY h.symm⟩ -- `IntermediateAgrees`: under `{A ← a}`, `M` evaluates to `hMequiv.symm m`. have hInter : P.IntermediateAgrees (Regime.single S.A (S.hAbool.symm a)) (Regime.single S.M (S.hMequiv.symm m)) ω := by intro v hv have hvM : v = S.M := Finset.mem_singleton.mp hv subst hvM -- `MofA a ω = m` ⇒ `hMequiv (P.eval r₁ ω M) = m` ⇒ `P.eval r₁ ω M = hMequiv.symm m`. have hM : S.hMequiv (P.eval (Regime.single S.A (S.hAbool.symm a)) ω S.M) = m := hω change P.eval (Regime.single S.A (S.hAbool.symm a)) ω S.M = S.hMequiv.symm m exact S.hMequiv.eq_symm_apply.mpr hM -- Apply `hC.composition`. have hComp := hC.composition (Regime.single S.A (S.hAbool.symm a)) (Regime.single S.M (S.hMequiv.symm m)) hdisj {S.Y} hY_notmem ω hInter -- Extract the `Y`-coordinate. have hYcoord : P.eval (Regime.single S.A (S.hAbool.symm a) |>.sqcup (Regime.single S.M (S.hMequiv.symm m)) hdisj) ω S.Y = P.eval (Regime.single S.A (S.hAbool.symm a)) ω S.Y := by simpa [POSystem.poVariable] using congrFun hComp ⟨S.Y, mem_singleton_self S.Y⟩ -- Push through `yVar.equiv`. change S.yVar.equiv (P.eval _ ω S.Y) = S.yVar.equiv (P.eval _ ω S.Y) exact congrArg S.yVar.equiv hYcoord
    Causalean.PO.POFrontdoorSystem.YofAM_eq_YofA_on_MofA_event · Causalean/PO/ID/Exact/Frontdoor.lean:356
  • integral_eq_sum_integral_MofA lemma — Partition of ∫ f along fibers of MofA a (finite codomain β).
    P :
    shared
    β :
    Type u_1
    shared
    f :
    P.Ω → ℝ
    hf :
    Integrable f P.μ
    a :
    ∫ ω, f ω ∂P.μ = ∑ m : β, ∫ ω in {ω' | S.MofA a ω' = m}, f ω ∂P.μ
    Proof (Lean source)
    lemma integral_eq_sum_integral_MofA (f : P.Ω → ℝ) (hf : Integrable f P.μ) (a : Bool) : ∫ ω, f ω ∂P.μ = ∑ m : β, ∫ ω in {ω' | S.MofA a ω' = m}, f ω ∂P.μ := by -- Sets `{ω | MofA a ω = m}` for `m : β` are the fibers of `MofA a`. set s : β → Set P.Ω := fun m => {ω | S.MofA a ω = m} with hs have hmeas : ∀ m, MeasurableSet (s m) := fun m => S.measurable_MofA a (MeasurableSet.singleton m) have hdisj : Pairwise (onFun Disjoint s) := by intro m₁ m₂ hne refine Set.disjoint_left.mpr ?_ intro ω hω₁ hω₂ apply hne simp only [Set.mem_setOf_eq, s] at hω₁ hω₂ exact hω₁ ▸ hω₂ have hcov : ⋃ m, s m = univ := by refine Set.eq_univ_of_forall (fun ω => ?_) exact Set.mem_iUnion.mpr ⟨S.MofA a ω, rfl⟩ have hintOn : ∀ m, IntegrableOn f (s m) P.μ := fun m => hf.integrableOn have hsplit : ∫ ω in ⋃ m, s m, f ω ∂P.μ = ∑ m : β, ∫ ω in s m, f ω ∂P.μ := MeasureTheory.integral_iUnion_fintype hmeas hdisj hintOn rw [← setIntegral_univ, ← hcov, hsplit]
    Causalean.PO.POFrontdoorSystem.integral_eq_sum_integral_MofA · Causalean/PO/ID/Exact/Frontdoor.lean:409
  • integral_eq_sum_eventCondExp_aEvent lemma — Bool-partition tower identity for eventCondExp.
    P :
    shared
    β :
    Type u_1
    shared
    g :
    P.Ω → ℝ
    hg :
    Integrable g P.μ
    ∫ ω, g ω ∂P.μ = ∑ a' : Bool, eventCondExp P.μ (S.aEvent a') g * (P.μ (S.aEvent a')).toReal
    Proof (Lean source)
    lemma integral_eq_sum_eventCondExp_aEvent (g : P.Ω → ℝ) (hg : Integrable g P.μ) : ∫ ω, g ω ∂P.μ = ∑ a' : Bool, eventCondExp P.μ (S.aEvent a') g * (P.μ (S.aEvent a')).toReal := by -- Rewrite each RHS term as a set integral. have hterm : ∀ a' : Bool, eventCondExp P.μ (S.aEvent a') g * (P.μ (S.aEvent a')).toReal = ∫ ω in S.aEvent a', g ω ∂P.μ := by intro a' unfold eventCondExp by_cases h0 : (P.μ (S.aEvent a')).toReal = 0 · -- Both sides are 0. rw [h0, mul_zero] have hμ0 : P.μ (S.aEvent a') = 0 := by rcases (ENNReal.toReal_eq_zero_iff _).mp h0 with h | h · exact h · exact absurd h (measure_ne_top _ _) exact (MeasureTheory.setIntegral_measure_zero g hμ0).symm · field_simp -- Swap the sum to set-integrals. have hsum : ∑ a' : Bool, eventCondExp P.μ (S.aEvent a') g * (P.μ (S.aEvent a')).toReal = ∑ a' : Bool, ∫ ω in S.aEvent a', g ω ∂P.μ := by exact Finset.sum_congr rfl (fun a' _ => hterm a') rw [hsum] -- Now prove `∫ g = ∑ a', ∫ in aEvent a', g`. have hmeas : ∀ a' : Bool, MeasurableSet (S.aEvent a') := S.measurableSet_aEvent have hdisj : Pairwise (onFun Disjoint (fun a' : Bool => S.aEvent a')) := by intro a₁ a₂ hne refine Set.disjoint_left.mpr ?_ intro ω hω₁ hω₂ apply hne show a₁ = a₂ have h1 : S.factualA ω = a₁ := hω₁ have h2 : S.factualA ω = a₂ := hω₂ exact h1.symm.trans h2 have hcov : ⋃ a' : Bool, S.aEvent a' = univ := by refine Set.eq_univ_of_forall (fun ω => ?_) exact Set.mem_iUnion.mpr ⟨S.factualA ω, rfl⟩ have hintOn : ∀ a' : Bool, IntegrableOn g (S.aEvent a') P.μ := fun _ => hg.integrableOn have hsplit : ∫ ω in ⋃ a' : Bool, S.aEvent a', g ω ∂P.μ = ∑ a' : Bool, ∫ ω in S.aEvent a', g ω ∂P.μ := MeasureTheory.integral_iUnion_fintype hmeas hdisj hintOn rw [← setIntegral_univ, ← hcov, hsplit]
    Causalean.PO.POFrontdoorSystem.integral_eq_sum_eventCondExp_aEvent · Causalean/PO/ID/Exact/Frontdoor.lean:434
LATE 22 core · 14 supporting This file formalizes the binary-instrument local average treatment effect in the potential-outcome framework. ★ POIVSystem★ late_wald

Instrumental Variables LATE

This file formalizes the binary-instrument local average treatment effect in the potential-outcome framework. It defines the IV subsystem POIVSystem, potential treatments DofZ, potential outcomes YofD, the complier event, event-conditional observable means, the IV assumption bundle, and the target LATE.

The proof surface decomposes the Wald argument into public identities: first_stage_identity, reduced_form_identity, pointwise_monotonicity, and event_conditioning_identity. The theorem late_wald assembles these pieces to identify the observable Wald ratio with the complier average treatment effect.

structure POIVSystem reviewed
Causalean.PO

A binary instrumental-variables subsystem (def:po-iv-system) records, within an ambient potential-outcome system, an instrument, a treatment, and an outcome, where the three nodes are required to be pairwise distinct.

Definition (Lean source)
P :
Z :
P.V
D :
P.V
Y :
P.V
hZbool :
P.X Z ≃ᵐ Bool
hDbool :
P.X D ≃ᵐ Bool
hYreal :
P.X Y ≃ᵐ ℝ
hZD :
Z ≠ D
hDY :
D ≠ Y
hZY :
Z ≠ Y
Causalean.PO.POIVSystem · Causalean/PO/ID/Exact/LATE.lean:38 · uses POSystem
def zVar reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the binary instrument potential-outcome variable is its instrument node with its binary representation.

Definition (Lean source)
P :
shared
S :
shared
zVar S :
⟨S.Z, S.hZbool⟩
def dVar reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the binary treatment potential-outcome variable is its treatment node with its binary representation.

Definition (Lean source)
P :
shared
S :
shared
dVar S :
⟨S.D, S.hDbool⟩
def yVar reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the real-valued outcome potential-outcome variable is its outcome node with its real-valued representation.

Definition (Lean source)
P :
shared
S :
shared
yVar S :
POVar P ℝ
⟨S.Y, S.hYreal⟩
def instrumentRegime reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the instrument intervention regime fixes the instrument to that value.

Definition (Lean source)
P :
shared
S :
shared
z :
instrumentRegime S z :
Regime P.V P.X
Regime.single S.Z (S.hZbool.symm z)
Causalean.PO.POIVSystem.instrumentRegime · Causalean/PO/ID/Exact/LATE.lean:65 · uses POIVSystem , POSystem , Regime
def treatmentRegime reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and a treatment value, the treatment intervention regime fixes treatment to that value.

Definition (Lean source)
P :
shared
S :
shared
d :
treatmentRegime S d :
Regime P.V P.X
Regime.single S.D (S.hDbool.symm d)
Causalean.PO.POIVSystem.treatmentRegime · Causalean/PO/ID/Exact/LATE.lean:69 · uses POIVSystem , POSystem , Regime
def DofZ reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the potential treatment assigns each unit the treatment it would take if the instrument were fixed to that value.

Definition (Lean source)
P :
shared
S :
shared
z :
DofZ S z :
P.Ω → Bool
S.dVar.cfUnder S.zVar z
Causalean.PO.POIVSystem.DofZ · Causalean/PO/ID/Exact/LATE.lean:73 · uses POIVSystem , POSystem
def YofD reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and a treatment value, the potential outcome assigns each unit the outcome it would have if treatment were fixed to that value.

Definition (Lean source)
P :
shared
S :
shared
d :
YofD S d :
P.Ω → ℝ
S.yVar.cfUnder S.dVar d
Causalean.PO.POIVSystem.YofD · Causalean/PO/ID/Exact/LATE.lean:82 · uses POIVSystem , POSystem
def factualZ reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the factual instrument assigns each unit its observed binary instrument.

Definition (Lean source)
P :
shared
S :
shared
factualZ S :
P.Ω → Bool
S.zVar.factual
Causalean.PO.POIVSystem.factualZ · Causalean/PO/ID/Exact/LATE.lean:91 · uses POIVSystem , POSystem
def factualD reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the factual treatment assigns each unit its observed binary treatment.

Definition (Lean source)
P :
shared
S :
shared
factualD S :
P.Ω → Bool
S.dVar.factual
Causalean.PO.POIVSystem.factualD · Causalean/PO/ID/Exact/LATE.lean:94 · uses POIVSystem , POSystem
def factualY reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the factual outcome assigns each unit its observed real outcome.

Definition (Lean source)
P :
shared
S :
shared
factualY S :
P.Ω → ℝ
S.yVar.factual
Causalean.PO.POIVSystem.factualY · Causalean/PO/ID/Exact/LATE.lean:97 · uses POIVSystem , POSystem
def complierEvent reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the complier event is the set of units that would take treatment when the instrument is on and would not take treatment when it is off.

Definition (Lean source)
P :
shared
S :
shared
complierEvent S :
Set P.Ω
{ ω | S.DofZ true ω = true ∧ S.DofZ false ω = false }
Causalean.PO.POIVSystem.complierEvent · Causalean/PO/ID/Exact/LATE.lean:100 · uses POIVSystem , POSystem
def zEvent reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the instrument event is the set of units whose observed instrument equals that value.

Definition (Lean source)
P :
shared
S :
shared
z :
zEvent S z :
Set P.Ω
S.zVar.event z
Causalean.PO.POIVSystem.zEvent · Causalean/PO/ID/Exact/LATE.lean:104 · uses POIVSystem , POSystem
def YofDofZ reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the outcome under the instrument-induced treatment assigns each unit its treated potential outcome if the instrument induces treatment and its untreated potential outcome otherwise.

Definition (Lean source)
P :
shared
S :
shared
z :
YofDofZ S z :
P.Ω → ℝ
fun ω => if S.DofZ z ω then S.YofD true ω else S.YofD false ω
Causalean.PO.POIVSystem.YofDofZ · Causalean/PO/ID/Exact/LATE.lean:138 · uses POIVSystem , POSystem
def condExpDZ reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the conditional treatment mean is the event-conditional mean of observed treatment among units with that instrument value.

Definition (Lean source)
P :
shared
S :
shared
z :
condExpDZ S z :
eventCondExp P.μ (S.zEvent z) (fun ω => ((S.factualD ω).toNat : ℝ))
Causalean.PO.POIVSystem.condExpDZ · Causalean/PO/ID/Exact/LATE.lean:150 · uses POIVSystem , POSystem
def condExpYZ reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the conditional outcome mean is the event-conditional mean of observed outcome among units with that instrument value.

Definition (Lean source)
P :
shared
S :
shared
z :
condExpYZ S z :
eventCondExp P.μ (S.zEvent z) S.factualY
Causalean.PO.POIVSystem.condExpYZ · Causalean/PO/ID/Exact/LATE.lean:158 · uses POIVSystem , POSystem
def dUnderZ reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and an instrument value, the treatment under the instrument regime is the potential treatment represented together with the intervention fixing the instrument to that value.

Definition (Lean source)
P :
shared
S :
shared
z :
dUnderZ S z :
⟨S.dVar, Regime.single S.Z (S.hZbool.symm z)⟩
def yUnderD reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system and a treatment value, the outcome under the treatment regime is the potential outcome represented together with the intervention fixing treatment to that value.

Definition (Lean source)
P :
shared
S :
shared
d :
yUnderD S d :
⟨S.yVar, Regime.single S.D (S.hDbool.symm d)⟩
def cfBundle reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the counterfactual bundle contains potential treatments under both instrument values and potential outcomes under both treatment values.

Definition (Lean source)
P :
shared
S :
shared
cfBundle S :
POCFBundle.cons (S.dUnderZ true) <| POCFBundle.cons (S.dUnderZ false) <| POCFBundle.cons (S.yUnderD true) <| POCFBundle.cons (S.yUnderD false) <| POCFBundle.nil P
structure Assumptions reviewed
Causalean.PO.POIVSystem

Classical binary-instrument IV assumptions (def:po-iv-assumptions). Bundles consistency (SUTVA): the observed treatment and outcome equal the realized potential treatment and outcome, instrument exogeneity: the instrument is independent of the full counterfactual bundle of potential treatments and outcomes, monotonicity (no defiers): turning the instrument on never moves a unit out of treatment, and relevance: the complier event has positive probability.

Definition (Lean source)
P :
shared
S :
consistency :
P.Consistency

Consistency (SUTVA): the observed D/Y equal the realized potential treatment/outcome (D = D(Z), Y = Y(D)). Links observed data to the counterfactuals. (Exclusion — Z affects Y only through D — is built into the Y(d) interface: outcomes carry no z argument, see the type docstring above.)

instrumentIndep :
P.IndepCF (RegimedVar.ofFactual S.zVar) S.cfBundle P.μ

Instrument independence (random/ignorable instrument): the instrument is independent of the full counterfactual bundle, Z ⟂ (D(1), D(0), Y(1), Y(0)). Phrased as independence of the factual instrument from the counterfactual bundle. This is the IV exogeneity condition.

monotonicity :
∀ᵐ ω ∂P.μ, S.DofZ false ω = true → S.DofZ true ω = true

Monotonicity (no defiers): turning the instrument on never moves a unit out of treatment — D(1) ≥ D(0) a.s. On Bool this is D(0)=1 → D(1)=1. Rules out defiers so the IV ratio identifies the complier effect.

relevance :
0 < (P.μ S.complierEvent).toReal

Relevance (non-trivial first stage): the complier event C = {D(1)=1, D(0)=0} has positive probability, so the instrument actually shifts treatment for a positive mass of units (the LATE denominator is non-zero).

Causalean.PO.POIVSystem.Assumptions · Causalean/PO/ID/Exact/LATE.lean:181 · uses POIVSystem , POSystem
def LATE reviewed
Causalean.PO.POIVSystem

For a binary instrumental-variables system, the local average treatment effect is the mean difference between treated and untreated potential outcomes among compliers, with value zero when the complier event has zero probability.

Definition (Lean source)
P :
shared
S :
shared
LATE S :
eventCondExp P.μ S.complierEvent (fun ω => S.YofD true ω - S.YofD false ω)
Causalean.PO.POIVSystem.LATE · Causalean/PO/ID/Exact/LATE.lean:215 · uses POIVSystem , POSystem
theorem late_wald reviewed
Causalean.PO.POIVSystem

Wald identification of LATE (prop:po-late). Under the binary- instrument LATE identifying assumption bundle, when the event {Z=1} has positive probability, the event {Z=0} has positive probability, and the potential outcomes under treatment and under control are integrable, the Wald ratio (E[Y|Z=1] − E[Y|Z=0]) / (E[D|Z=1] − E[D|Z=0]) equals the local average treatment effect LATE.

Formal statement
P :
shared
S :
shared
hA :
S.Assumptions
hZ1 :
0 < (P.μ (S.zEvent true)).toReal
hZ0 :
0 < (P.μ (S.zEvent false)).toReal
hY1 :
Integrable (S.YofD true) P.μ
hY0 :
Integrable (S.YofD false) P.μ
(S.condExpYZ true - S.condExpYZ false) / (S.condExpDZ true - S.condExpDZ false) = S.LATE
Proof (Lean source)
theorem late_wald (hA : S.Assumptions) (hZ1 : 0 < (P.μ (S.zEvent true)).toReal) (hZ0 : 0 < (P.μ (S.zEvent false)).toReal) (hY1 : Integrable (S.YofD true) P.μ) (hY0 : Integrable (S.YofD false) P.μ) : (S.condExpYZ true - S.condExpYZ false) / (S.condExpDZ true - S.condExpDZ false) = S.LATE := by rw [S.first_stage_identity hA hZ1 hZ0] rw [S.reduced_form_identity hA hZ1 hZ0 hY1 hY0] have heq : ∀ᵐ ω ∂P.μ, S.YofDofZ true ω - S.YofDofZ false ω = (S.YofD true ω - S.YofD false ω) * S.complierEvent.indicator (fun _ => (1:ℝ)) ω := S.pointwise_monotonicity hA rw [MeasureTheory.integral_congr_ae heq] rw [S.event_conditioning_identity] have hC : (P.μ S.complierEvent).toReal ≠ 0 := ne_of_gt hA.relevance field_simp
14 supporting declarations (lemmas, instances)
  • measurable_DofZ lemma — The potential treatment under a fixed instrument value is measurable.
    P :
    shared
    S :
    shared
    z :
    Measurable (S.DofZ z)
    Proof (Lean source)
    @[fun_prop] lemma measurable_DofZ (z : Bool) : Measurable (S.DofZ z) := S.dVar.measurable_cfUnder S.zVar z
    Causalean.PO.POIVSystem.measurable_DofZ · Causalean/PO/ID/Exact/LATE.lean:107
  • measurable_factualZ lemma — The factual instrument is measurable.
    P :
    shared
    S :
    shared
    Measurable S.factualZ
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualZ : Measurable S.factualZ := S.zVar.measurable_factual
    Causalean.PO.POIVSystem.measurable_factualZ · Causalean/PO/ID/Exact/LATE.lean:112
  • measurable_factualD lemma — The factual treatment is measurable.
    P :
    shared
    S :
    shared
    Measurable S.factualD
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualD : Measurable S.factualD := S.dVar.measurable_factual
    Causalean.PO.POIVSystem.measurable_factualD · Causalean/PO/ID/Exact/LATE.lean:116
  • measurable_factualY lemma — The factual outcome is measurable.
    P :
    shared
    S :
    shared
    Measurable S.factualY
    Proof (Lean source)
    @[fun_prop] lemma measurable_factualY : Measurable S.factualY := S.yVar.measurable_factual
    Causalean.PO.POIVSystem.measurable_factualY · Causalean/PO/ID/Exact/LATE.lean:120
  • measurable_YofD lemma — The potential outcome under a fixed treatment value is measurable.
    P :
    shared
    S :
    shared
    d :
    Measurable (S.YofD d)
    Proof (Lean source)
    @[fun_prop] lemma measurable_YofD (d : Bool) : Measurable (S.YofD d) := S.yVar.measurable_cfUnder S.dVar d
    Causalean.PO.POIVSystem.measurable_YofD · Causalean/PO/ID/Exact/LATE.lean:124
  • measurableSet_complierEvent lemma — The complier event is measurable.
    P :
    shared
    S :
    shared
    MeasurableSet S.complierEvent
    Proof (Lean source)
    lemma measurableSet_complierEvent : MeasurableSet S.complierEvent := (S.measurable_DofZ true (MeasurableSpace.measurableSet_top (s := {true}))).inter (S.measurable_DofZ false (MeasurableSpace.measurableSet_top (s := {false})))
    Causalean.PO.POIVSystem.measurableSet_complierEvent · Causalean/PO/ID/Exact/LATE.lean:129
  • measurableSet_zEvent lemma — The factual instrument event is measurable.
    P :
    shared
    S :
    shared
    z :
    MeasurableSet (S.zEvent z)
    Proof (Lean source)
    lemma measurableSet_zEvent (z : Bool) : MeasurableSet (S.zEvent z) := S.zVar.measurableSet_event _ (measurableSet_singleton _)
    Causalean.PO.POIVSystem.measurableSet_zEvent · Causalean/PO/ID/Exact/LATE.lean:134
  • YofDofZ_def lemma — The potential outcome under the treatment that an instrument value induces sends a unit to that unit's treated potential outcome when the induced treatment is one, and to its untreated potential outcome otherwise.
    P :
    shared
    S :
    shared
    z :
    S.YofDofZ z = fun ω => if S.DofZ z ω then S.YofD true ω else S.YofD false ω
    Proof (Lean source)
    @[causal_defs_simps] lemma YofDofZ_def (z : Bool) : S.YofDofZ z = fun ω => if S.DofZ z ω then S.YofD true ω else S.YofD false ω := rfl
    Causalean.PO.POIVSystem.YofDofZ_def · Causalean/PO/ID/Exact/LATE.lean:142
  • DofZ_eq_factualD_on_zEvent lemma — On zEvent z, the counterfactual treatment D(z) equals the factual D. Pointwise specialization of Consistency.factual with r = instrumentRegime z, Y = {D}.
    P :
    shared
    S :
    shared
    hA :
    S.Assumptions
    z :
    ω :
    P.Ω
    :
    ω ∈ S.zEvent z
    S.DofZ z ω = S.factualD ω
    Proof (Lean source)
    lemma DofZ_eq_factualD_on_zEvent (hA : S.Assumptions) (z : Bool) {ω : P.Ω} (hω : ω ∈ S.zEvent z) : S.DofZ z ω = S.factualD ω := POVar.cf_eq_factual_on_event hA.consistency S.dVar S.zVar z S.hZD.symm hω
    Causalean.PO.POIVSystem.DofZ_eq_factualD_on_zEvent · Causalean/PO/ID/Exact/LATE.lean:226
  • factualY_eq_YofD_factualD lemma — Factual Y equals the counterfactual Y(factualD ω). Pointwise specialization of Consistency.factual with r = treatmentRegime (factualD ω), Y = {Y}.
    P :
    shared
    S :
    shared
    hA :
    S.Assumptions
    ω :
    P.Ω
    S.factualY ω = S.YofD (S.factualD ω) ω
    Proof (Lean source)
    lemma factualY_eq_YofD_factualD (hA : S.Assumptions) (ω : P.Ω) : S.factualY ω = S.YofD (S.factualD ω) ω := POVar.factual_eq_cfUnder_self_selected hA.consistency S.yVar S.dVar S.hDY.symm ω
    Causalean.PO.POIVSystem.factualY_eq_YofD_factualD · Causalean/PO/ID/Exact/LATE.lean:234
  • first_stage_identity theorem — Step 1 of rem:po-late: first-stage identity. E[D | Z=1] - E[D | Z=0] = P(C).
    P :
    shared
    S :
    shared
    hA :
    S.Assumptions
    hZ1 :
    0 < (P.μ (S.zEvent true)).toReal
    hZ0 :
    0 < (P.μ (S.zEvent false)).toReal
    S.condExpDZ true - S.condExpDZ false = (P.μ S.complierEvent).toReal
    Proof (Lean source)
    theorem first_stage_identity (hA : S.Assumptions) (hZ1 : 0 < (P.μ (S.zEvent true)).toReal) (hZ0 : 0 < (P.μ (S.zEvent false)).toReal) : S.condExpDZ true - S.condExpDZ false = (P.μ S.complierEvent).toReal := by -- Step 1: `condExpDZ z = ∫ (DofZ z ω).toNat ∂μ`. have hμne_zero : ∀ z, 0 < (P.μ (S.zEvent z)).toReal → P.μ (S.zVar.event z) ≠ 0 := fun z hZ h => absurd hZ (by simp [show S.zEvent z = S.zVar.event z from rfl, h]) have hμne_top : ∀ z, P.μ (S.zVar.event z) ≠ ⊤ := fun _ => measure_ne_top _ _ have hCE : ∀ z (_hZ : 0 < (P.μ (S.zEvent z)).toReal), S.condExpDZ z = ∫ ω, ((S.DofZ z ω).toNat : ℝ) ∂P.μ := by intro z hZ -- `h_proj` on the bundle `jointValue`: indices 0,1 are `D(1),D(0)`. let h_proj : (∀ i : Fin S.cfBundle.n, S.cfBundle.type i) → ℝ := fun f => ((cond z ((f (0 : Fin 4)) : Bool) ((f (1 : Fin 4)) : Bool)).toNat : ℝ) have hh_meas : Measurable h_proj := by let instCf : ∀ a : Fin 4, MeasurableSpace (S.cfBundle.type a) := fun a => S.cfBundle.inst a change Measurable fun f : ∀ i : Fin S.cfBundle.n, S.cfBundle.type i => ((cond z ((f (0 : Fin 4)) : Bool) ((f (1 : Fin 4)) : Bool)).toNat : ℝ) cases z · exact (by fun_prop : Measurable fun n : ℕ => (n : ℝ)).comp ((by fun_prop : Measurable Bool.toNat).comp (measurable_pi_apply (1 : Fin 4))) · exact (by fun_prop : Measurable fun n : ℕ => (n : ℝ)).comp ((by fun_prop : Measurable Bool.toNat).comp (measurable_pi_apply (0 : Fin 4))) have h_cons : ∀ ω ∈ S.zVar.event z, ((S.factualD ω).toNat : ℝ) = h_proj (S.cfBundle.jointValue ω) := by intro ω hω rw [← S.DofZ_eq_factualD_on_zEvent hA z hω] change ((S.DofZ z ω).toNat : ℝ) = ((cond z ((S.cfBundle.jointValue ω (0 : Fin 4)) : Bool) ((S.cfBundle.jointValue ω (1 : Fin 4)) : Bool)).toNat : ℝ) cases z <;> rfl have hbridge : S.condExpDZ z = eventCondExp P.μ (S.zVar.event z) (fun ω => ((S.factualD ω).toNat : ℝ)) := rfl rw [hbridge, POSystem.eventCondExp_of_consistency_IndepCF hA.instrumentIndep (a := S.zVar) hh_meas (measurableSet_singleton z) (ae_restrict_of_forall_mem (S.measurableSet_zEvent z) h_cons) (hμne_zero z hZ) (hμne_top z)] refine MeasureTheory.integral_congr_ae (Filter.Eventually.of_forall ?_) intro ω change ((cond z ((S.cfBundle.jointValue ω (0 : Fin 4)) : Bool) ((S.cfBundle.jointValue ω (1 : Fin 4)) : Bool)).toNat : ℝ) = ((S.DofZ z ω).toNat : ℝ) cases z <;> rfl rw [hCE true hZ1, hCE false hZ0] -- Step 2: fold the two integrals into `∫ ((DofZ true).toNat - (DofZ false).toNat) ∂μ`. have hDbdd : ∀ z, ∀ ω, |((S.DofZ z ω).toNat : ℝ)| ≤ 1 := fun z ω => by cases S.DofZ z ω <;> simp have hDint : ∀ z, Integrable (fun ω => ((S.DofZ z ω).toNat : ℝ)) P.μ := fun z => (MeasureTheory.integrable_const (1:ℝ)).mono' ((by fun_prop : Measurable (fun n : ℕ => (n : ℝ))).comp ((by fun_prop : Measurable Bool.toNat).comp (S.measurable_DofZ z)) |>.aestronglyMeasurable) (Filter.Eventually.of_forall (hDbdd z)) rw [← MeasureTheory.integral_sub (hDint true) (hDint false)] -- Step 3: under monotonicity, `(DofZ true).toNat - (DofZ false).toNat = 1_C a.s.`. have hInd : ∀ᵐ ω ∂P.μ, ((S.DofZ true ω).toNat : ℝ) - ((S.DofZ false ω).toNat : ℝ) = S.complierEvent.indicator (fun _ => (1:ℝ)) ω := by refine hA.monotonicity.mono (fun ω hω => ?_) by_cases h1 : S.DofZ true ω = true · by_cases h0 : S.DofZ false ω = true · have hnC : ω ∉ S.complierEvent := by intro ⟨_, h0'⟩; rw [h0] at h0'; exact Bool.noConfusion h0' simp [h1, h0, Set.indicator_of_notMem hnC] · have h0' : S.DofZ false ω = false := Bool.not_eq_true _ |>.mp h0 have hC : ω ∈ S.complierEvent := ⟨h1, h0'⟩ simp [h1, h0', Set.indicator_of_mem hC] · have h1' : S.DofZ true ω = false := Bool.not_eq_true _ |>.mp h1 by_cases h0 : S.DofZ false ω = true · exfalso; rw [hω h0] at h1'; exact Bool.noConfusion h1'.symm · have h0' : S.DofZ false ω = false := Bool.not_eq_true _ |>.mp h0 have hnC : ω ∉ S.complierEvent := by intro ⟨h1'', _⟩; rw [h1'] at h1''; exact Bool.false_ne_true h1'' simp [h1', h0', Set.indicator_of_notMem hnC] rw [MeasureTheory.integral_congr_ae hInd] rw [MeasureTheory.integral_indicator_const (1:ℝ) S.measurableSet_complierEvent] simp [MeasureTheory.measureReal_def]
    Causalean.PO.POIVSystem.first_stage_identity · Causalean/PO/ID/Exact/LATE.lean:241
  • reduced_form_identity theorem — Step 2 of rem:po-late: reduced-form identity. E[Y | Z=1] - E[Y | Z=0] = E[Y(D(1)) - Y(D(0))].
    P :
    shared
    S :
    shared
    hA :
    S.Assumptions
    hZ1 :
    0 < (P.μ (S.zEvent true)).toReal
    hZ0 :
    0 < (P.μ (S.zEvent false)).toReal
    hY1 :
    Integrable (S.YofD true) P.μ
    hY0 :
    Integrable (S.YofD false) P.μ
    S.condExpYZ true - S.condExpYZ false = ∫ ω, (S.YofDofZ true ω - S.YofDofZ false ω) ∂P.μ
    Proof (Lean source)
    theorem reduced_form_identity (hA : S.Assumptions) (hZ1 : 0 < (P.μ (S.zEvent true)).toReal) (hZ0 : 0 < (P.μ (S.zEvent false)).toReal) (hY1 : Integrable (S.YofD true) P.μ) (hY0 : Integrable (S.YofD false) P.μ) : S.condExpYZ true - S.condExpYZ false = ∫ ω, (S.YofDofZ true ω - S.YofDofZ false ω) ∂P.μ := by -- Measurability and integrability of `YofDofZ z`. have hYDZ_meas : ∀ z, Measurable (S.YofDofZ z) := fun z => by unfold YofDofZ exact Measurable.ite (S.measurable_DofZ z (MeasurableSet.singleton true)) (S.measurable_YofD true) (S.measurable_YofD false) have hYDZ_bdd : ∀ z, ∀ ω, |S.YofDofZ z ω| ≤ |S.YofD true ω| + |S.YofD false ω| := fun z ω => by have h1 := abs_nonneg (S.YofD true ω) have h0 := abs_nonneg (S.YofD false ω) unfold YofDofZ; cases S.DofZ z ω <;> simp [h1, h0] have hYDZ_int : ∀ z, Integrable (S.YofDofZ z) P.μ := fun z => (hY1.norm.add hY0.norm).mono' (hYDZ_meas z).aestronglyMeasurable (Filter.Eventually.of_forall (hYDZ_bdd z)) -- Step 1: `condExpYZ z = ∫ YofDofZ z ω ∂μ`. have hμne_zero : ∀ z, 0 < (P.μ (S.zEvent z)).toReal → P.μ (S.zVar.event z) ≠ 0 := fun z hZ h => absurd hZ (by simp [show S.zEvent z = S.zVar.event z from rfl, h]) have hμne_top : ∀ z, P.μ (S.zVar.event z) ≠ ⊤ := fun _ => measure_ne_top _ _ have hCE : ∀ z (_hZ : 0 < (P.μ (S.zEvent z)).toReal), S.condExpYZ z = ∫ ω, S.YofDofZ z ω ∂P.μ := by intro z hZ -- `h_proj` on the bundle: indices 0,1 are `D(1),D(0)`; 2,3 are `Y(1),Y(0)`. let h_proj : (∀ i : Fin S.cfBundle.n, S.cfBundle.type i) → ℝ := fun f => if ((cond z ((f (0 : Fin 4)) : Bool) ((f (1 : Fin 4)) : Bool)) : Bool) then ((f (2 : Fin 4)) : ℝ) else ((f (3 : Fin 4)) : ℝ) have hh_meas : Measurable h_proj := by let instCf : ∀ a : Fin 4, MeasurableSpace (S.cfBundle.type a) := fun a => S.cfBundle.inst a change Measurable fun f : ∀ i : Fin S.cfBundle.n, S.cfBundle.type i => if ((cond z ((f (0 : Fin 4)) : Bool) ((f (1 : Fin 4)) : Bool)) : Bool) then ((f (2 : Fin 4)) : ℝ) else ((f (3 : Fin 4)) : ℝ) cases z · refine Measurable.ite ?_ ?_ ?_ · exact (by fun_prop : Measurable fun f : ∀ i : Fin S.cfBundle.n, S.cfBundle.type i => ((f (1 : Fin 4)) : Bool)) (MeasurableSet.singleton true) · exact measurable_pi_apply (2 : Fin 4) · exact measurable_pi_apply (3 : Fin 4) · refine Measurable.ite ?_ ?_ ?_ · exact (by fun_prop : Measurable fun f : ∀ i : Fin S.cfBundle.n, S.cfBundle.type i => ((f (0 : Fin 4)) : Bool)) (MeasurableSet.singleton true) · exact measurable_pi_apply (2 : Fin 4) · exact measurable_pi_apply (3 : Fin 4) have h_cons : ∀ ω ∈ S.zVar.event z, S.factualY ω = h_proj (S.cfBundle.jointValue ω) := by intro ω hω rw [S.factualY_eq_YofD_factualD hA ω, ← S.DofZ_eq_factualD_on_zEvent hA z hω] have hJV0 : (S.cfBundle.jointValue ω (0 : Fin 4) : Bool) = S.DofZ true ω := rfl have hJV1 : (S.cfBundle.jointValue ω (1 : Fin 4) : Bool) = S.DofZ false ω := rfl have hJV2 : (S.cfBundle.jointValue ω (2 : Fin 4) : ℝ) = S.YofD true ω := rfl have hJV3 : (S.cfBundle.jointValue ω (3 : Fin 4) : ℝ) = S.YofD false ω := rfl change S.YofD (S.DofZ z ω) ω = if ((cond z ((S.cfBundle.jointValue ω (0 : Fin 4)) : Bool) ((S.cfBundle.jointValue ω (1 : Fin 4)) : Bool)) : Bool) then ((S.cfBundle.jointValue ω (2 : Fin 4)) : ℝ) else ((S.cfBundle.jointValue ω (3 : Fin 4)) : ℝ) rw [hJV0, hJV1, hJV2, hJV3] cases z <;> cases S.DofZ _ ω <;> simp have hbridge : S.condExpYZ z = eventCondExp P.μ (S.zVar.event z) S.factualY := rfl rw [hbridge, POSystem.eventCondExp_of_consistency_IndepCF hA.instrumentIndep (a := S.zVar) hh_meas (measurableSet_singleton z) (ae_restrict_of_forall_mem (S.measurableSet_zEvent z) h_cons) (hμne_zero z hZ) (hμne_top z)] refine MeasureTheory.integral_congr_ae (Filter.Eventually.of_forall ?_) intro ω change (if ((cond z ((S.cfBundle.jointValue ω (0 : Fin 4)) : Bool) ((S.cfBundle.jointValue ω (1 : Fin 4)) : Bool)) : Bool) then ((S.cfBundle.jointValue ω (2 : Fin 4)) : ℝ) else ((S.cfBundle.jointValue ω (3 : Fin 4)) : ℝ)) = S.YofDofZ z ω unfold YofDofZ cases z <;> rfl rw [hCE true hZ1, hCE false hZ0] rw [← MeasureTheory.integral_sub (hYDZ_int true) (hYDZ_int false)]
    Causalean.PO.POIVSystem.reduced_form_identity · Causalean/PO/ID/Exact/LATE.lean:326
  • pointwise_monotonicity theorem — Step 3 of rem:po-late: pointwise monotonicity identity. Y(D(1)) - Y(D(0)) = (Y(1) - Y(0)) · 1_C almost surely.
    P :
    shared
    S :
    shared
    hA :
    S.Assumptions
    ∀ᵐ ω ∂P.μ, S.YofDofZ true ω - S.YofDofZ false ω
    = (S.YofD true ω - S.YofD false ω) * S.complierEvent.indicator (fun _ => (1:ℝ)) ω
    Proof (Lean source)
    theorem pointwise_monotonicity (hA : S.Assumptions) : ∀ᵐ ω ∂P.μ, S.YofDofZ true ω - S.YofDofZ false ω = (S.YofD true ω - S.YofD false ω) * S.complierEvent.indicator (fun _ => (1:ℝ)) ω := by refine hA.monotonicity.mono (fun ω hω => ?_) unfold YofDofZ complierEvent rcases hD1 : S.DofZ true ω <;> rcases hD0 : S.DofZ false ω <;> simp_all [indicator]
    Causalean.PO.POIVSystem.pointwise_monotonicity · Causalean/PO/ID/Exact/LATE.lean:413
  • event_conditioning_identity theorem — Step 4 of rem:po-late: event-conditioning identity. E[(Y(1) - Y(0)) · 1_C] = P(C) · LATE.
    P :
    shared
    S :
    shared
    ∫ ω, (S.YofD true ω - S.YofD false ω) * S.complierEvent.indicator (fun _ => (1:ℝ)) ω ∂P.μ
    = (P.μ S.complierEvent).toReal * S.LATE
    Proof (Lean source)
    theorem event_conditioning_identity : ∫ ω, (S.YofD true ω - S.YofD false ω) * S.complierEvent.indicator (fun _ => (1:ℝ)) ω ∂P.μ = (P.μ S.complierEvent).toReal * S.LATE := by unfold LATE eventCondExp have hC : MeasurableSet S.complierEvent := S.measurableSet_complierEvent have h_rw : (fun ω => (S.YofD true ω - S.YofD false ω) * S.complierEvent.indicator (fun _ => (1:ℝ)) ω) = S.complierEvent.indicator (fun ω => S.YofD true ω - S.YofD false ω) := by funext ω by_cases hω : ω ∈ S.complierEvent · simp [Set.indicator_of_mem hω] · simp [Set.indicator_of_notMem hω] rw [h_rw, MeasureTheory.integral_indicator hC] by_cases hμ : (P.μ S.complierEvent).toReal = 0 · rw [hμ, zero_mul] have hμ0 : P.μ S.complierEvent = 0 := by have hne : P.μ S.complierEvent ≠ ⊤ := measure_ne_top _ _ exact (ENNReal.toReal_eq_zero_iff _).mp hμ |>.resolve_right hne have hrest : P.μ.restrict S.complierEvent = 0 := by rw [MeasureTheory.Measure.restrict_eq_zero]; exact hμ0 simp [hrest] · field_simp
    Causalean.PO.POIVSystem.event_conditioning_identity · Causalean/PO/ID/Exact/LATE.lean:425