Sharp variance estimator and causal bootstrap in stratified randomized experiments

Abstract

Randomized experiments are the gold standard for estimating treatment effects, and randomization serves as a reasoned basis for inference. In widely used stratified randomized experiments, randomization-based finite-population asymptotic theory enables valid inference for the average treatment effect, relying on normal approximation and a Neyman-type conservative variance estimator. However, when the sample size is small or the outcomes are skewed, the Neyman-type variance estimator may become overly conservative, and the normal approximation can fail. To address these issues, we propose a sharp variance estimator and two causal bootstrap methods to more accurately approximate the sampling distribution of the weighted difference-in-means estimator in stratified randomized experiments. The first causal bootstrap procedure is based on rank-preserving imputation and we prove its second-order refinement over normal approximation. The second causal bootstrap procedure is based on constant-treatment-effect imputation and is further applicable in paired experiments. In contrast to traditional bootstrap methods, where randomness originates from hypothetical super-population sampling, our analysis for the proposed causal bootstrap is randomization-based, relying solely on the randomness of treatment assignment in randomized experiments. Numerical studies and two real data applications demonstrate advantages of our proposed methods in finite samples. The \texttt{R} package \texttt{CausalBootstrap} implementing our method is publicly available.

Accepted by Statistics in Medicine

References in corpus (16)

• Sharp bounds on the variance in randomized experiments
• Randomization Tests for Weak Null Hypotheses in Randomized Experiments
• Design-Based Ratio Estimators and Central Limit Theorems for Clustered, Blocked RCTs
• Gaussian Prepivoting for Finite Population Causal Inference
• Insights on Variance Estimation for Blocked and Matched Pairs Designs
• Rerandomization in stratified randomized experiments
• Concentration of normalized sums and a central limit theorem for noncorrelated random variables
• Regression-adjusted average treatment effect estimates in stratified randomized experiments
• Bootstrap Inference for Quantile Treatment Effects in Randomized Experiments with Matched Pairs
• Quantile Treatment Effects and Bootstrap Inference under Covariate-Adaptive Randomization
• Neymanian inference in randomized experiments
• Integer Programming for Generalized Causal Bootstrap Designs
• Optimized variance estimation under interference and complex experimental designs
• Sharp bounds for variance of treatment effect estimators in the finite population in the presence of covariates
• Sharp Bounds on the Variance of General Regression Adjustment in Randomized Experiments
• A Fast Bootstrap Algorithm for Causal Inference with Large Data