REVIEW 5 cited by
Doubly robust inference via calibration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Doubly robust estimators are widely used for estimating average treatment effects and other linear summaries of regression functions. While consistency requires only one of two nuisance functions to be estimated consistently, asymptotic normality typically require sufficiently fast convergence of both. In this work, we correct this mismatch: we show that calibrating the nuisance estimators within a doubly robust procedure yields doubly robust asymptotic normality for linear functionals. We introduce a general framework, calibrated debiased machine learning (calibrated DML), and propose a specific estimator that augments standard DML with a simple isotonic regression adjustment. Our theoretical analysis shows that the calibrated DML estimator remains asymptotically normal if either the regression or the Riesz representer of the functional is estimated sufficiently well, allowing the other to converge arbitrarily slowly or even inconsistently. We further propose a simple bootstrap method for constructing confidence intervals, enabling doubly robust inference without additional nuisance estimation. In a range of semi-synthetic benchmark datasets, calibrated DML reduces bias and improves coverage relative to standard DML. Our method can be integrated into existing DML pipelines by adding just a few lines of code to calibrate cross-fitted estimates via isotonic regression.
Forward citations
Cited by 5 Pith papers
-
Optimal use of a black-box learner in semiparametric estimation
For black-box nuisance estimators in the partial linear model, a new estimator attains the optimal error rate n^{-1/2}+δa,μ δa,π+δs^2, improving on DML and matched by a lower bound.
-
Fitted Occupancy-Ratio Evaluation without Bellman Completeness
FORE estimates discounted occupancy ratios by iterating KL-projected adjoint Bellman updates, achieving convergence under ratio realizability alone without Bellman completeness.
-
Model-Agnostic Bounds for Augmented Inverse Probability Weighted Estimators' Wald-Confidence Interval Coverage in Randomized Controlled Trials
First Berry-Esseen-type coverage bounds for AIPW Wald intervals with estimated variance in RCTs show cross-fitting can improve coverage through variance overestimation.
-
On regression with estimated covariates and conditional effects given the propensity score
New debiased estimators for regression on an estimated propensity score can approach oracle rates, with the corrected plug-in reaching n^{-2/5} under explicit accuracy conditions.
-
Nonparametric estimation of an optimal treatment rule with fused randomized trials and missing effect modifiers
A doubly robust estimator learns individualized treatment rules from pooled randomized trials when one effect modifier is missing in some trials, applied to opioid use disorder medications.
Discussion (0). Continue with ORCID to comment.