Semiparametric Bayesian causal inference

DOI10.1214/19-AOS1919zbMATH Open1471.62348arXiv1808.04246OpenAlexW3104714948WikidataQ130493975 ScholiaQ130493975MaRDI QIDQ2215769FDOQ2215769

Authors: Kolyan Ray, Aad van der Vaart 

Publication date: 14 December 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We develop a semiparametric Bayesian approach for estimating the mean response in a missing data model with binary outcomes and a nonparametrically modelled propensity score. Equivalently we estimate the causal effect of a treatment, correcting nonparametrically for confounding. We show that standard Gaussian process priors satisfy a semiparametric Bernstein-von Mises theorem under smoothness conditions. We further propose a novel propensity score-dependent prior that provides efficient inference under strictly weaker conditions. We also show that it is theoretically preferable to model the covariate distribution with a Dirichlet process or Bayesian bootstrap, rather than modelling the covariate density using a Gaussian process prior.

Full work available at URL: https://arxiv.org/abs/1808.04246

Recommendations

• Semiparametric Bayesian estimation for marginal parametric potential outcome modeling: application to causal inference
• Semiparametric Bayesian doubly robust causal estimation
• A Bayesian nonparametric approach to causal inference on quantiles
• A Bayesian nonparametric causal model
• A Bayesian Semiparametric Approach to Intermediate Variables in Causal Inference

zbMATH Keywords

causal inferenceGaussian processesDirichlet processBernstein-von Mises processpropensity score-dependent priors

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Gaussian processes (60G15) Nonparametric tolerance and confidence regions (62G15)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Asymptotic Statistics
• Recursive partitioning for heterogeneous causal effects
• Gaussian processes for machine learning.
• Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
• Causal inference for statistics, social, and biomedical sciences. An introduction
• Information rates of nonparametric Gaussian process methods
• Exchangeably weighted bootstraps of the general empirical process
• Prior distributions on spaces of probability measures
• Mathematical foundations of infinite-dimensional statistical models
• Higher order influence functions and minimax estimation of nonlinear functionals
• The central role of the propensity score in observational studies for causal effects
• A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect
• Fundamentals of nonparametric Bayesian inference
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• Introduction to double robust methods for incomplete data
• Title not available (Why is that?)
• Information and asymptotic efficiency in parametric-nonparametric models
• Minimax estimation of a functional on a structured high-dimensional model
• Semiparametric minimax rates
• Bayesian inference for causal effects: The role of randomization
• Title not available (Why is that?)
• A semiparametric Bernstein-von Mises theorem for Gaussian process priors
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models
• On the Bernstein-von Mises theorem with infinite-dimensional parameters
• The Bayesian analysis of complex, high-dimensional models: can it be CODA?
• Higher order tangent spaces and influence functions
• The semiparametric Bernstein-von Mises theorem
• Semiparametric Efficiency in Multivariate Regression Models with Missing Data
• On differentiable functionals
• Lower bounds for posterior rates with Gaussian process priors
• On Profile Likelihood
• Bernstein-von Mises theorem for linear functionals of the density
• Rates of contraction of posterior distributions based on Gaussian process priors
• Rates of contraction for posterior distributions in \(L^{r}\)-metrics, \(1 \leq r \leq \infty\)
• Treatment effects: a Bayesian perspective
• Inference for semiparametric models: Some questions and an answer. (With comments)
• Bayesian inference with rescaled Gaussian process priors
• Pushing the Limits of Contemporary Statistics: Contributions in Honor of Jayanta K. Ghosh
• Title not available (Why is that?)
• Regularization and confounding in linear regression for treatment effect estimation

Cited In (16)

• A semiparametric modeling approach using Bayesian additive regression trees with an application to evaluate heterogeneous treatment effects
• Causal inference: a missing data perspective
• A Bayesian nonparametric approach to causal inference on quantiles
• Semiparametric Bayesian estimation for marginal parametric potential outcome modeling: application to causal inference
• Bayesian matrix completion approach to causal inference with panel data
• The how and why of Bayesian nonparametric causal inference
• Semiparametric Bayesian doubly robust causal estimation
• A Bayesian view of doubly robust causal inference: Table 1.
• On the Bernstein-von Mises theorem for the Dirichlet process
• Simulation‐based estimators of analytically intractable causal effects
• Causal estimation using semiparametric transformation models under prevalent sampling
• In Nonparametric and High-Dimensional Models, Bayesian Ignorability is an Informative Prior
• A Bayesian Semiparametric Approach to Intermediate Variables in Causal Inference
• Estimating the effects of a California gun control program with multitask Gaussian processes
• A Bayesian nonparametric causal model
• Causal inference under mis-specification: adjustment based on the propensity score (with discussion)

This page was built for publication: Semiparametric Bayesian causal inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215769)