Longitudinal causal inference under informative missingness using the self-censoring model

2026-10-06

AI Summary

This study addresses the bias in causal inference caused by missing not at random (MNAR) mechanisms in longitudinal observational data. Building upon the self-censoring model, this work introduces shadow variable moment conditions and machine learning techniques, proposing a recursive identification formula and a pooled smoothing strategy to overcome information borrowing challenges under sparse measurements. Furthermore, nuisance function estimation is achieved by integrating path derivatives, cross-fitting, and ensemble learning. The primary contribution lies in constructing an asymptotically linear estimator that attains root-n consistent estimation of longitudinal modified treatment policy effects while enabling simultaneous inference across multiple time points.

Abstract

Longitudinal observational data are often subject to informative missingness. For example, in healthcare research using electronic health records, covariates and outcomes are measured only when patients interact with the healthcare system. Whether these data are observed usually depends on the unobserved variable values themselves, introducing a common form of data missing not at random. We develop identification and estimation methods for the effects of longitudinal modified treatment policies under a self-censoring model which explicitly models this dependence. We consider effects of treatments that can be modified only at measurement times (e.g., interactions with the heathcare system). We study two settings: one in which the observed history suffices for treatment confounding control, and another in which confounder control requires covariate values that were not measured at missed visits. In both settings, we combine longitudinal causal identification with shadow-variable conditional moment restrictions to obtain recursive identification formulas for the counterfactual outcome mean. We derive gradients of the pathwise derivatives and second-order remainder expansions, and use these results to construct estimators that accommodate machine learning for nuisance-function estimation. Under suitable product-rate conditions and cross-fitting, the estimators are asymptotically linear and permit root-n inference, including simultaneous inference across outcome times. We also describe conditional-moment learning and ensemble approaches for estimating the nuisance functions required by our approach, together with a pool-and-smooth strategy that borrows information across sparsely measured outcomes.

Problem

• Longitudinal causal inference
• Informative missingness
• Self-censoring model
• Missing not at random
• Modified treatment policies

Innovation

• Longitudinal causal inference
• Informative missingness
• Self-censoring model
• Shadow-variable conditional moment restrictions
• Machine learning