Chapter 11

Regression Models on Longitudinal Propensity Scores

Aristide Achy-BrouMichael GriswoldConstantine Frangakis


11.1 Introduction

11.2 Estimation Using Regression on Longitudinal Propensity Scores

11.3 Example

11.4 Summary




Estimating causal treatment effect in longitudinal, observational data can be complex due to the need to control for selection bias in the full history of covariates used in the treatment assignment. Having a robust approach to deal with the lack of randomization between treatment groups is critical because the history of covariates used in the treatment assignment grows rapidly with the length of the observation period.

We present regression estimators that can compare longitudinal treatments ...

Get Analysis of Observational Health Care Data Using SAS now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.