MixWild & MixRegLS
These are statistical software programs for analysis of intensive longitudinal data, or other types of data with many within-subject (or cluster) measurements. MixRegLS allows modeling of the mean, between-subject (BS) variance, and within-subject (WS) variance. Random effects are included in the mean (location) and WS variance (scale) submodels. The MixWild program extends MixRegLS in several important ways. MixWild allows for multiple random location effects (e.g., intercepts and slopes), in addition to a random scale effect. These random subject effects (multiple location and one scale) can then be used as predictors in a Stage 2 model of a subject or multilevel outcome that could be continuous (multiple regression), discrete (binary/ordinal or nominal logistic regression), or a count (Poisson regression). Also, MixWild includes a graphical user interface (GUI) to facilitate program use.
- Dzubur, E., Ponnada, A., Nordgren, R., Yang, C.-H., Intille, S., Dunton, G., & Hedeker, D. (2020). MixWILD: A program for examining the effects of variance and slope of time-varying variables in intensive longitudinal data. Behavior Research Methods, 52(4):1403-1427. pdf file
MixRegLS program – this zip file contains the MIXREGLS program, manual, and several examples
- exercise dataset and def file: zip file