Assessing the Robustness of Growth Mixture Models with Distal Outcomes Across Different Time Coding Approaches
Growth mixture models (GMMs) with distal outcomes identify groups following different trajectories and examine group differences in subsequent outcomes. Although time coding is often treated as a matter of parameter interpretation, it may also affect model estimation, class recovery, and distal-outcome inference. We examined this sensitivity through two empirical illustrations and simulation studies varying time coding, data conditions, and population trajectory patterns. Alternative codings sometimes selected different numbers of classes. Even with the number of classes fixed, fitted models differed in convergence and attained log-likelihood solutions, accompanied by differences in class recovery and distal-outcome estimates. These discrepancies were most pronounced when the population contained more classes. Moreover, the relative performance of each coding varied across trajectory patterns, with no coding performing consistently best. Researchers should therefore select a primary coding based on substantive interpretation and examine sensitivity across alternative codings, particularly when many classes are considered, or estimation is unstable.
Authors
- Zsuzsa Bakk (ORCID: https://orcid.org/0000-0001-9352-4812)
- Mark de Rooij (ORCID: https://orcid.org/0000-0001-7308-6210)
- Ethan Michael McCormick (ORCID: https://orcid.org/0000-0002-7919-4340)
- Yuqi Liu
Publication Details
- Journal
- Figshare
- Published
- 2026-11-19
- DOI
- https://doi.org/10.6084/m9.figshare.35068189
- Primary Topic
- Psychometric Methodologies and Testing
- Type
- article
- Field-Weighted Citation Impact
- 0.00