Single- and Double-Cross Validation for Mode Selection Using Fit Indexes in Latent Profile Analysis

• In Event: Measurement Invariance, Model Selection, and Measurement Uncertainty in Structural Equation Modeling

Abstract

The purpose of this simulation study is to examine the performance of cross validation (e.g., single, double) using common fit indices in LPA to help researchers select the best approximating model while varying design factors. We will examine the performance of fit index using single-, double-, and pseudo-cross validation in LPA models. This study is an extension of Whittaker’s and Miller’s (2021) work that focused on cross-validation indices in latent class models. Factors for the simulation study were selected to mirror conditions found in applied research in educational and psychological research

Authors

• Hiroki Matsuo, Baylor University
  Presenting Author

• Grant B. Morgan, Baylor University
  Presenting Author