Related Experiment Videos
Fitting mixed-effects models for repeated ordinal outcomes with the NLMIXED procedure
1Department of Psychology, DePaul University, 2219 North Kenmore Ave., Chicago, IL 60614-3522, USA. csheu@condor.depaul.edu
Behavior Research Methods, Instruments, & Computers : a Journal of the Psychonomic Society, Inc
|July 12, 2002
Summary
This study analyzes repeated ordinal outcomes using mixed-effects models, demonstrating their application in psychological research. The findings facilitate the use of these advanced statistical methods for longitudinal data analysis.
Area of Science:
- Psychology
- Statistics
- Biostatistics
Background:
- Repeated ordinal outcomes are common in psychological studies.
- Traditional methods may not adequately handle the complexity of such data.
Purpose of the Study:
- To present an analysis of repeated ordinal outcomes from two psychological studies.
- To facilitate the use of mixed-effects models for analyzing this type of data.
Main Methods:
- Utilized mixed-effects regression within a longitudinal design.
- Employed generalized linear models with random effects.
- Used the NLMIXED procedure in SAS for model fitting.
Main Results:
- Successfully applied mixed-effects models to repeated ordinal outcomes.
- Demonstrated the parallel between model specifications and SAS statements.
Conclusions:
- Mixed-effects models are effective for analyzing repeated ordinal outcomes.
- The paper provides a practical guide for researchers using SAS for such analyses.