A review and evaluation of standard methods to handle missing data on time-varying confounders in marginal structural models

TL;DR

This paper reviews and compares methods for handling missing data in time-varying confounders within marginal structural models, highlighting the strengths and limitations of each approach through simulation studies.

Contribution

It provides a comprehensive evaluation of existing missing data methods in MSMs and offers guidance on their performance under various missingness mechanisms.

Findings

Complete case analysis is generally biased.

Multiple imputation and IPMW perform well under certain conditions.

LOCF is unbiased only in specific non-random missingness scenarios.

Abstract

Marginal structural models (MSMs) are commonly used to estimate causal intervention effects in longitudinal non-randomised studies. A common issue when analysing data from observational studies is the presence of incomplete confounder data, which might lead to bias in the intervention effect estimates if they are not handled properly in the statistical analysis. However, there is currently no recommendation on how to address missing data on covariates in MSMs under a variety of missingness mechanisms encountered in practice. We reviewed existing methods to handling missing data in MSMs and performed a simulation study to compare the performance of complete case (CC) analysis, the last observation carried forward (LOCF), the missingness pattern approach (MPA), multiple imputation (MI) and inverse-probability-of-missingness weighting (IPMW). We considered three mechanisms for non-monotone missing data which are common in observational studies using electronic health record data. Whereas CC analysis lead to biased estimates of the intervention effect in almost all scenarios, the performance of the other approaches varied across scenarios. The LOCF approach led to unbiased estimates only under a specific non-random mechanism in which confounder values were missing when their values remained unchanged since the previous measurement. In this scenario, MI, the MPA and IPMW were biased. MI and IPMW led to the estimation of unbiased effects when data were missing at random, given the covariates or the treatment but only MI was unbiased when the outcome was a predictor of missingness. Furthermore, IPMW generally lead to very large standard errors. Lastly, regardless of the missingness mechanism, the MPA led to unbiased estimates only when the failure to record a confounder at a given time-point modified the subsequent relationships between the partially observed covariate and the outcome.