R and Mplus 8 syntax for the nlpsem package companion manuscript: Examination of Nonlinear Longitudinal Processes with Latent Variables, Latent Processes, Latent Changes, and Latent Classes in the Structural Equation Modeling Framework: The R package nlpsem.
This repository is the reproducibility companion for the nlpsem statistical software project. It demonstrates nonlinear longitudinal modeling examples in both R/OpenMx and Mplus 8, giving reviewers a clear bridge between statistical methodology, implementation, and manuscript-facing examples.
| Folder | Contents | What it demonstrates |
|---|---|---|
Demo_for_nlpsem/ |
R Markdown and rendered Markdown synthetic examples for nlpsem. |
Package-level examples, reproducible demonstration workflow, and user-facing statistical documentation. |
Demo_for_OpenMx/ |
R/OpenMx scripts for latent change, bilinear spline growth, mediation, factor-mixture, growth-mixture, and posterior-class workflows. | Direct OpenMx implementation of nonlinear longitudinal and latent-variable models. |
Demo_for_Mplus8/ |
Mplus 8 input files for corresponding latent growth, latent change, mixture, and mixture-of-experts examples. | Cross-software reproducibility and translation between R/OpenMx and Mplus syntax. |
This repo demonstrates:
- reproducible statistical-methods documentation
- nonlinear longitudinal modeling with latent variables, latent processes, latent changes, and latent classes
- translation between R/OpenMx and Mplus model specifications
- measurement-science communication for technical and applied audiences
- companion-material organization for manuscript and software review
The repo is not an AI-modeling repository directly. Its relevance to AI evaluation is methodological: longitudinal and latent-variable measurement principles help frame how system behavior changes across repeated conditions, how hidden sources of variation can be modeled, and how reliability should be documented for reviewers.
nlpsem: R package for nonlinear longitudinal models in the structural equation modeling framework.
MIT. See LICENSE.