The analysis of repeated measures designs: A review

Department of Psychology, University of Manitoba, 190 Dysart Road, Winnipeg, Manitoba, Canada R3T 2N2.
British Journal of Mathematical and Statistical Psychology (Impact Factor: 1.53). 06/2001; 54(Pt 1):1-20. DOI: 10.1348/000711001159357
Source: PubMed

ABSTRACT Repeated measures ANOVA can refer to many different types of analysis. Specifically, this vague term can refer to conventional tests of significance, one of three univariate solutions with adjusted degrees of freedom, two different types of multivariate statistic, or approaches that combine univariate and multivariate tests. Accordingly, it is argued that, by only reporting probability values and referring to statistical analyses as repeated measures ANOVA, authors convey neither the type of analysis that was used nor the validity of the reported probability value, since each of these approaches has its own strengths and weaknesses. The various approaches are presented with a discussion of their strengths and weaknesses, and recommendations are made regarding the 'best' choice of analysis. Additional topics discussed include analyses for missing data and tests of linear contrasts.


Available from: Harvey Jay Keselman, Jun 03, 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Linear mixed-effects models (LMMs) are increasingly being used for data analysis in cognitive neuroscience and experimental psychology, where within-participant designs are common. The current article provides an introductory review of the use of LMMs for within-participant data analysis and describes a free, simple, graphical user interface (LMMgui). LMMgui uses the package lme4 (Bates et al., 2014a,b) in the statistical environment R (R Core Team).
    Frontiers in Psychology 01/2015; 6:2. DOI:10.3389/fpsyg.2015.00002 · 2.80 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this study was to compare the effectiveness of work-related cognitive-behavioral treatment (W-CBT) with that of cognitive-behavioral treatment as usual (CBT-AU) for employees on sick leave as a result of a major depressive disorder (MDD). We collected data for 26 matched outpatients at pre- and posttreatment, as well as at 1-year follow-up. Outcome measures were the days of incapacity to work (DIW) as well as self-report measures (Beck Depression Inventory [BDI], Symptom Checklist 90-R [GSI], Life Satisfaction Questionnaire [FLZ]). We analyzed data with hierarchical linear modeling in a 2-level model. Therapy effects were defined in 3 ways: effect size (ES), response (based on the reliable change index), and remission compared with the general population's symptom level. The DIW were reduced significantly after both types of treatment, but employees showed even fewer DIW after W-CBT. At follow-up, significantly more employees were working as a result of W-CBT than with CBT-AU. Significant improvements on scores of self-rating measures corresponded with moderate-to-large effect sizes for both treatment types. Approximately 2 thirds of the treated employees were categorized as unimpaired on BDI scores at posttreatment and at follow-up. At least 1 half of the employees were classified as unimpaired on GSI scores at both assessment points. In future research, a randomized controlled trial should be conducted using a larger sample size to investigate the impact of moderators (e.g., employees at different branches of the company). Findings provided support for using common CBT techniques to enhance return to work without losing expected improvements at the symptom level. (PsycINFO Database Record (c) 2014 APA, all rights reserved).
    Journal of Occupational Health Psychology 11/2014; 20(2). DOI:10.1037/a0038341 · 2.07 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This study examined the relationship between objectively measured nocturnal hot flashes and objectively measured sleep in breast cancer survivors with insomnia. Twenty-four women who had completed treatment for non-metastatic breast cancer participated. All were enrolled in a study of cognitive–behavioral treatment for chronic insomnia. Nocturnal hot flashes and sleep were measured by skin conductance and polysomnography, respectively. The 10-minute periods around hot flashes were found to have significantly more wake time, and more stage changes to lighter sleep, than other 10-minute periods during the night. Nights with hot flashes had a significantly higher percentage of wake time, a lower percentage of Stage 2 sleep, and a longer REM latency compared to nights without hot flashes. Overall, hot flashes were found to be associated with less efficient, more disrupted sleep. Nocturnal hot flashes, or their underlying mechanisms, should be considered as potential contributors to sleep disruption in women with breast cancer who report poor sleep.
    Journal of Pain and Symptom Management 06/2004; 27(6):513-522. DOI:10.1016/S0885-3924(04)00114-9 · 2.74 Impact Factor