A New Tool for Old Questions: The Sequence-Analysis Multistate Model to Study Relationships Between Time-Varying Covariates and Trajectories.
The relationship between processes and time-varying covariates is of central theoretical interest in many social science research questions. On the one hand, event history analysis has been the method chosen to study the relationship between time-varying covariates and outcomes that can meaningfully be specified as simple instantaneous events or transitions. On the other hand, sequence analysis has made increasing inroads into the social sciences to analyze trajectories as holistic “process outcomes.” However, it does not allow for studying their relationship with time-varying covariates.We propose the sequence analysis multistate model (SAMM) that combines the advantages of both approaches. SAMM models the relationship between time-varying covariates and trajectories of categorical states specified as process outcomes that unfold over time. It proceeds in two steps. First, we use an adapted sequence analysis to identify typical sequencing and spacing between main transitions in trajectories. Second, we adapt multistate models to estimate the chances to follow each kind of the identified typical sequence. The usefulness of SAMM is illustrated with an example from life course sociology on how (1) time-varying family status is associated with women’s employment trajectories in East and West Germany, and (2) how the German reunification affected these trajectories in the two sub-societies.
Literature:
Blossfeld, H. and Rohwer, G. (2002). Techniques of Event History Modeling, New Approaches to Causal Analysis. Mahwah NJ: Lawrence Erlbaum, 2nd edition.