Research on timing of foster care outcomes: One methodological problem and approaches to its solution

This article discusses the use of event history analysis, specifically the Cox proportional hazards model, in research on timing of foster care outcomes. It focuses on the inclusion of autocorrelated data in the model, a statistical problem that has received little attention in studies of the timing of exit from or reentry into foster care. This article describes the Cox model, the problem posed by use of the model with autocorrelated data, and promising solutions to the problem. It focuses on one solution, the WLW (Wei, Lin, and Weissfeld 1989) model, and shows its benefits with data drawn from the authors' research program.