Applying mixed regression models to the analysis of repeated-measures data in psychosomatic medicine

Ekin Blackwell*, Carlos F Mendes De Leon, Gregory E. Miller

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

97 Scopus citations


OBJECTIVE: Although repeated-measures designs are increasingly common in research on psychosomatic medicine, they are not well suited to the conventional statistical techniques that scientists often apply to them. The goal of this article is to introduce readers to mixed regression models, which provide a more flexible and accurate framework for managing repeated-measures data. METHODS AND RESULTS: We begin with a summary of the advantages that mixed regression models have over conventional statistical techniques in the context of repeated-measures designs. Next, we outline the conceptual and mathematical underpinnings of mixed regression models for a nonstatistical audience. The article ends with two examples of how these models can be applied in psychosomatic research; one deals with a prospective investigation of depressive symptoms and change in body mass index in older adults and the other with a diary study of social interactions and cortisol secretion. CONCLUSIONS: Mixed regression models offer a flexible and powerful approach to analyzing repeated-measures data. They possess important advantages over more traditional strategies, and more widespread application of these models is likely to enhance the overall quality of psychosomatic research.

Original languageEnglish (US)
Pages (from-to)870-878
Number of pages9
JournalPsychosomatic medicine
Issue number6
StatePublished - 2006


  • Analysis of change
  • Mixed regression models
  • Nested designs
  • Random effects
  • Repeated measures

ASJC Scopus subject areas

  • Applied Psychology
  • Psychiatry and Mental health

Fingerprint Dive into the research topics of 'Applying mixed regression models to the analysis of repeated-measures data in psychosomatic medicine'. Together they form a unique fingerprint.

Cite this