Causal Inference with Confounders MNAR under Treatment-independent Missingness Assumption

TL;DR

This paper develops a framework for identifying and estimating causal effects in observational studies with confounders missing not at random, assuming treatment-independent missingness, and demonstrates its effectiveness through simulations and real data.

Contribution

It introduces a general identification framework for causal inference with treatment-independent missing confounders and proposes estimators for causal effects under this setting.

Findings

Proposed a weighted estimation method for model parameters.

Developed three estimators for average causal effect.

Validated estimators with simulations and real data.

Abstract

Causal inference in observational studies can be challenging when confounders are subject to missingness. Generally, the identification of causal effects is not guaranteed even under restrictive parametric model assumptions when confounders are missing not at random. To address this, We propose a general framework to establish the identification of causal effects when confounders are subject to treatment-independent missingness, which means that the missing data mechanism is independent of the treatment, given the outcome and possibly missing confounders. We give special consideration to commonly-used models for continuous and binary outcomes and provide counterexamples when identification fails. For estimation, we provide a weighted estimation equation estimating method for model parameters and purpose three estimators for the average causal effect based on the estimated models. We evaluate the finite-sample performance of the estimators via simulations. We further illustrate the proposed method with real data sets from the National Health and Nutrition Examination Survey.