Using Repeated Measures Regression Mixture Model When Sample Size Is Small

• In Event: 32.082 - Roundtable Session 11
  In Roundtable Session: 32.082-16 - Structural Equation Modeling With Difficult Data

Abstract

Regression mixture models are used to identify the heterogeneity in the effects of interest on an outcome(s) when the group membership is unobserved. The current study aims to propose using a regression mixture model with repeated measures to overcome the model instability under two conditions: (1) a low reliability of the measure or (2) a small sample size. When researchers are interested in finding the differential effect and so desire to employ regression mixture models, one alternative can be collecting 1 or 2 more measurements from the same participants. Monte Carlo simulations are used to show the improved model stability of regression mixtures when using repeated measures in terms of the class enumeration and the accuracy of parameter estimates.

Author

• Minjung Kim, The Ohio State University