Estimating Discrete-Time Survival Models as Structural Equation Models

Shawn Bauldry, University of North Carolina at Chapel Hill
Kenneth Bollen, University of North Carolina at Chapel Hill

Survival analysis is a common tool in the analysis of the timing of events. Survival models have been applied to a vast number of areas of sociological research. In this paper we show how to embed survival models in structural equation models (SEMs) while taking advantage of additional features possible in a SEM approach. Using empirical examples of time to promotion and timing of intercourse, we show that we can replicate the more traditional survival model results, but more importantly, we show how to control for measurement error and permit mediating variables. By doing so, we provide additional options useful to sociologists who use survival models.