Robust Estimation of the Causal Effect of Time-Varying Neighborhood Factors on Health Outcomes

• Activity Number: 502 - Propensity Score Methods to Conduct Observational Studies Using Complex Survey Data
• Type: Topic Contributed
• Date/Time: Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Michael Robbins* and Beth Ann Griffin and Regina Shih and Mary Slaughter
• Companies: RAND Corporation and RAND Corporation and RAND Corporation and RAND Corporation
• Keywords: Causality; Doubly robust; Health status disparities; Inverse probability of treatment weighting; Kernel density; Neighborhood

Abstract

The main difficulty of establishing causal relationships between an exposure and an outcome in observational data involves disentangling causality from confounding factors. This problem underlies much of neighborhoods research, which abounds with studies that consider associations between neighborhood characteristics and health outcomes in longitudinal data. Techniques commonly used for causal inference in longitudinal data, such as inverse probability of treatment weighting (IPTW) may be inappropriate in neighborhoods data. We introduce an IPTW method based on a multivariate kernel density which is more appropriate for neighborhoods data. The proposed method is applied in conjunction with a marginal structural model. Our empirical analyses use longitudinal data from the Health and Retirement Study. Our exposure of interest is neighborhood socioeconomic status (NSES); we examine its influence on cognitive function. Our findings illustrate the importance of the choice of method for IPTW; the comparison methods provide poor balance across the set of covariates and yield misleading results when applied in the outcomes models. The multivariate kernel is also validated via simulation.