Discontinuous growth models: illustrations, recommendations, and an R function for generating the design matrix
Paul D. Bliese, Jason Kautz, Jonas W. B. Lang
Abstract
The discontinuous growth model is a variant of a growth model that uses a block of time-related covariates to capture (1) immediate change and (2) changes in growth trajectories associated with one or more discrete events. Events might be planned, such as adding a trust violation to a longitudinal study of trust, or unplanned, such as examining the effects of the great recession on firm performance. In this chapter, we describe the discontinuous growth model and provide examples of research questions that can be tested using the models. We also provide detailed code in R to help researchers estimate the models. Throughout the chapter we give practical advice based on our experience estimating these models in different research contexts. Finally, we introduce an R function to help researchers set up the design matrix in situations where events occur at different points for the higher-level entities.