When analyzing longitudinal data, do you use regression or structural equation based approaches? There are many types of longitudinal data and different approaches to analyzing them. Two popular approaches are a regression based approach and a structural equation modeling based approach.
The regression-based approach comes in many flavors, including random effects models, multilevel models, econometric fixed effects models, and repeated measures ANOVA.
And the structural equation modeling approach is very flexible and includes options like latent growth curve models and growth mixture models.
In this training, we’ll compare the good, the bad, and the ugly of using these approaches in different longitudinal data scenarios:
- Multiple responses by multiple subjects
- Single observation per subject but have multiple subjects nested within a higher structure
- Multiple time periods where the time between periods is consistent
- Multiple time periods where the time is inconsistent
- Varying length of time between two consecutive periods between subjects
- Heterogeneous response patterns
- Mediation effect with predictor, mediator and dependent variable measured at different time points
This presentation compares and contrasts the use of regression and SEM models for analyzing the various types of longitudinal data.
Note: This training is a benefit to members of the Statistically Speaking Membership Program and part of the Stat’s Amore Trainings Series.
About the Instructor
Jeff Meyer is a statistical consultant with The Analysis Factor, a stats mentor for Statistically Speaking membership, and a workshop instructor. Read more about Jeff here.
Just head over and sign up for Statistically Speaking.
You'll get access to this training webinar, 130+ other stats trainings, a pathway to work through the trainings that you need — plus the expert guidance you need to build statistical skill with live Q&A sessions and an ask-a-mentor forum.