Trajectory Models Revisited: Assessing Recent Simulation Studies

• In Event: New Applications and Controversies in Survival and Trajectory Models

Abstract

Criminologists have a long-standing interest in analyzing age-graded trajectories of offending. Analytic approaches and statistical models proposed for this type of data include optimal matching sequence analysis, group-based trajectory models, growth mixture models, latent class transition models, grade of membership models, and unimodal curve registration models, among others. In the last several years, an increasing number of simulations studies have been conducted attempting to study merits and flaws of various procedures for the analysis of age-graded trajectories. For example, recently, Warren, et al. (2015) used simulated data to show that different trajectory models provided different results and often fail to reproduce the correct population model. We critically reexamine the logic and limitations of using simulations to shed light on alternate trajectory models. We emphasize the importance of considering the crucial assumptions that distinguish models when applying them to a substantive process. We argue that simulation studies have limitations often unacknowledged by researchers.

Authors

• Ross L. Matsueda, University of Washington

• Bryan D. Martin, University of Washington

• Elena A. Erosheva, University of Washington