Bootstrap consistency for general semiparametric $M$-estimation

Abstract

Consider $M$-estimation in a semiparametric model that is characterized by a Euclidean parameter of interest and an infinite-dimensional nuisance parameter. As a general purpose approach to statistical inferences, the bootstrap has found wide applications in semiparametric $M$-estimation and, because of its simplicity, provides an attractive alternative to the inference approach based on the asymptotic distribution theory. The purpose of this paper is to provide theoretical justifications for the use of bootstrap as a semiparametric inferential tool. We show that, under general conditions, the bootstrap is asymptotically consistent in estimating the distribution of the $M$-estimate of Euclidean parameter; that is, the bootstrap distribution asymptotically imitates the distribution of the $M$-estimate. We also show that the bootstrap confidence set has the asymptotically correct coverage probability. These general conclusions hold, in particular, when the nuisance parameter is not estimable at root-$n$ rate, and apply to a broad class of bootstrap methods with exchangeable bootstrap weights. This paper provides a first general theoretical study of the bootstrap in semiparametric models.

Published in at http://dx.doi.org/10.1214/10-AOS809 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (5)

• Inconsistency of bootstrap: The Grenander estimator
• Penalized log-likelihood estimation for partly linear transformation models with current status data
• General frequentist properties of the posterior profile distribution
• Semiparametric detection of significant activation for brain fMRI
• Higher order semiparametric frequentist inference with the profile sampler

Cited by in corpus (17)

• Empirical Process Results for Exchangeable Arrays
• Semiparametric inference in mixture models with predictive recursion marginal likelihood
• Joint asymptotics for semi-nonparametric regression models with partially linear structure
• General bootstrap for dual phi-divergence estimates
• Direct and approximately valid probabilistic inference on a class of statistical functionals
• Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data
• More Efficient Estimation for Logistic Regression with Optimal Subsample
• Bootstrap inference for panel data quantile regression
• Bootstrapping Two-phase Sampling
• Wild Residual Bootstrap Inference for Penalized Quantile Regression with Heteroscedastic Errors
• Complex sampling designs: uniform limit theorems and applications
• Robustness and Tractability for Non-convex M-estimators
• Inference problems in binary regression model with misclassified responses
• Resampling-based Confidence Intervals for Model-free Robust Inference on Optimal Treatment Regimes
• Multiplier U-processes: sharp bounds and applications
• Inference with penalized likelihood
• Refinements of the Kiefer-Wolfowitz Theorem and a Test of Concavity