Translating PROC GLIMMIX Models

[Franosei]

Summary

The article compares SAS and R implementations across common GLIMMIX use cases, including binary GLMMs, repeated-measures models, structured covariance models, count models, ordinal outcomes, and post-fit inference.

Main changes

• Added a structured article: R vs SAS: Translating PROC GLIMMIX Models.
• Included scenario-level comparisons between SAS PROC GLIMMIX and R packages.
• Documented package recommendations for lme4, glmmTMB, nlme, mmrm, geepack, emmeans, and ordinal.
• Added guidance on data preparation checks, equivalence criteria, direct versus approximate translation, and common sources of differences.
• Included references and session information for reproducibility.

The article focuses on whether the same statistical model, estimand, covariance structure, and post-fit interpretation can be reproduced or closely approximated in R.

Some scenarios are direct translations, while others are described as approximate or sensitivity-based where the R implementation does not exactly match the SAS PROC GLIMMIX specification.