Power and sample size for reversible linear mixed models with clustering and longitudinality: GLIMMPSE Version 3

Deborah H Glueck, Qian Li, Alasdair J Macleod, Elizabeth M Litkowski, Xi Yang, Jiang Bian, Albert D Ritzhaupt, Max Sommer, Natercia Valle, Jessica R Shaw and Keith E Muller

PLOS ONE, 2025, vol. 20, issue 9, 1-28

Abstract: GLIMMPSE Version 3 is a free, web-based, open-source software tool, which calculates power and sample size for general linear mixed models with Gaussian errors. The software permits power calculations for clinical trials, randomized experiments, and observational studies with clustering, repeated measures, and both, and almost any testable hypothesis. The software has been supported by five United States National Institutes of Health (NIH) grants, is used for more than 14,000 power or sample size calculations per year, has been cited in almost 500 peer-reviewed manuscripts, and used to design more than 200 million dollars in NIH-funded studies. This release provides several new features. The back end has been refactored in Python. The interface has been simplified, requiring user decisions about only one topic per screen. A new menu improves specification of both between-participant and within-participant hypotheses. A recursive algorithm permits computing covariances for up to ten levels of clustering. An updated Monte Carlo simulation using five new examples with clustering, longitudinality, or both, shows accuracy of the power approximations to within 0.01. Five new examples demonstrate power or sample size calculations for 1) a cluster-randomized trial, 2) a longitudinal study with repeated measures, 3) a multilevel study with a multivariate outcome, 4) a multilevel and longitudinal study, and 5) a complex study with a subgroup factor, repeated measures, and intervention-by-location interaction.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0329712 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 29712&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0329712

DOI: 10.1371/journal.pone.0329712

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().