Abstract
This chapter describes the integration of propensity score analysis in Latent class analysis (LCA) with covariates. In the current investigation, one can use data from a National Longitudinal Study of US adolescents and young adults to investigate the association between adolescent depression risk and early adult substance use. The chapter begins with a brief introduction to the latent class mathematical model, followed by a description of propensity score analysis for drawing causal inferences from observational data. It moves to empirical demonstration of incorporating propensity score weighting with LCA with covariates in order to estimate the causal effect of adolescent depression risk on adult substance use class membership. Gender is considered as a moderator of the average causal effect (ACE) of adolescent depression risk on young adult substance use profile. The chapter concludes with commentary on this integrated approach and recommendations for future research.
Original language | English (US) |
---|---|
Title of host publication | Statistics and Causality |
Subtitle of host publication | Methods for Applied Empirical Research |
Publisher | wiley |
Pages | 385-404 |
Number of pages | 20 |
ISBN (Electronic) | 9781118947074 |
ISBN (Print) | 9781118947043 |
DOIs | |
State | Published - Jan 1 2016 |
All Science Journal Classification (ASJC) codes
- General Social Sciences
- General Mathematics
- General Psychology