A simple sample size formula for analysis of covariance in cluster randomized trials
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
For cluster randomized trials with a continuous outcome, the sample size is often calculated as if an analysis of the outcomes at the end of the treatment period (follow‐up scores) would be performed. However, often a baseline measurement of the outcome is available or feasible to obtain. An analysis of covariance (ANCOVA) using both the baseline and follow‐up score of the outcome will then have more power. We calculate the efficiency of an ANCOVA analysis using the baseline scores compared with an analysis on follow‐up scores only. The sample size for such an ANCOVA analysis is a factor r2 smaller, where r is the correlation of the cluster means between baseline and follow‐up. This correlation can be expressed in clinically interpretable parameters: the correlation between baseline and follow‐up of subjects (subject autocorrelation) and that of clusters (cluster autocorrelation). Because of this, subject matter knowledge can be used to provide (range of) plausible values for these correlations, when estimates from previous studies are lacking. Depending on how large the subject and cluster autocorrelations are, analysis of covariance can substantially reduce the number of clusters needed. Copyright © 2012 John Wiley & Sons, Ltd.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Design and analysis of group-randomized trials: a review of recent methodological developments
Murray, D. M., Varnell, S. P., & Blitstein, J. L. (2004) · American Journal of Public Health · doi:10.2105/ajph.94.3.423 · Cited by 677 · cited 11×
“The ICC used is the unadjusted ICC: if the ICC already accounts for the outcome at baseline, the usual sample size applies: Œ1C .n 1/ adj N with adj the adjusted ICC and N the sample size according to a t -test on the follow-up scores.”
BackgroundInfluentialStatistical analysis and optimal design for cluster randomized trials.
Raudenbush, S. W. (1997) · Psychological Methods · doi:10.1037/1082-989x.2.2.173 · Cited by 636
Eldridge, S. M., Ashby, D., & Kerry, S. (2006) · International Journal of Epidemiology · doi:10.1093/ije/dyl129 · Cited by 529 · cited 1×
“(d) How uncertainty in the ICC is dealt with [17, 18] (e) How variation of the cluster sizes is accounted for [19, 20].”
BackgroundSelf-citationMethods to reduce the impact of intraclass correlation in group-randomized trials.
Murray, D. M., & Blitstein, J. L. (2003) · Evaluation Review · doi:10.1177/0193841x02239019 · Cited by 221 · cited 11×
“The ICC used is the unadjusted ICC: if the ICC already accounts for the outcome at baseline, the usual sample size applies: Œ1C .n 1/ adj N with adj the adjusted ICC and N the sample size according to a t -test on the follow-up scores.”
BackgroundInfluential
Cited by
The stepped wedge cluster randomised trial: rationale, design, analysis, and reporting
Hemming, K., Haines, T. P., Chilton, P. J., Girling, A. J., & Lilford, R. J. (2015) · BMJ · doi:10.1136/bmj.h391 · Cited by 1,410
“11 Under this design observations are made during a baseline period (before any cluster is randomised to receive the intervention) and again in a post-intervention period (where clusters randomised to the intervention have switched to receiving the intervention).”
Backgroundvan der Kolk, N. M., de Vries, N. M., Kessels, R. P. C., Joosten, H., Zwinderman, A. H., Post, B., & Bloem, B. R. (2019) · The Lancet Neurology · doi:10.1016/s1474-4422(19)30285-6 · Cited by 565
Methods for sample size determination in cluster randomized trials
Rutterford, C., Copas, A., & Eldridge, S. (2015) · International Journal of Epidemiology · doi:10.1093/ije/dyv113 · Cited by 429
Self-citationStepped wedge designs could reduce the required sample size in cluster randomized trials
Woertman, W., de Hoop, E., Moerbeek, M., Zuidema, S. U., Gerritsen, D. L., & Teerenstra, S. (2013) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2013.01.009 · Cited by 298
Self-citationHooper, R., Teerenstra, S., de Hoop, E., & Eldridge, S. (2016) · Statistics in Medicine · doi:10.1002/sim.7028 · Cited by 261
Self-citationHemming, K., Lilford, R., & Girling, A. J. (2015) · Statistics in Medicine · doi:10.1002/sim.6325 · Cited by 236
“However, others have shown that an alternative way of establishing power in the parallel CRT with baseline measures is to consider the design as a conventional parallel CRT, adjusting for baseline measures [13].”
BackgroundMethodInfluentialSample size calculations for stepped wedge and cluster randomised trials: a unified approach
Hemming, K., & Taljaard, M. (2016) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2015.08.015 · Cited by 230
“The CRT design with before and after observations When the parallel CRT is augmented to include an equal number of measurements before and after randomization, the corresponding design effect is [3]:”
Review of recent methodological developments in group-randomized trials: part 2—analysis
Turner, E. L., Prague, M., Gallis, J. A., Li, F., & Murray, D. M. (2017) · American Journal of Public Health · doi:10.2105/ajph.2017.303707 · Cited by 195
French, S. A., Sherwood, N. E., Veblen-Mortenson, S., Crain, A. L., JaKa, M. M., Mitchell, N. R., Hotop, A. M., Berge, J. M., Kunin Batson, A. S., Truesdale, K., et al. (2018) · American Journal of Public Health · doi:10.2105/ajph.2018.304696 · Cited by 70
Makai, P., Perry, M., Robben, S. H., Schers, H. J., Heinen, M. M., Olde Rikkert, M. G., & Melis, R. F. (2014) · Journal of Medical Internet Research · doi:10.2196/jmir.3057 · Cited by 59
“Effects were determined using linear mixed models within a highly efficient analysis of covariance (ANCOVA) framework [21] to allow for clustering within a primary care center.”
MethodContamination: How much can an individually randomized trial tolerate?
Hemming, K., Taljaard, M., Moerbeek, M., & Forbes, A. (2021) · Statistics in Medicine · doi:10.1002/sim.8958 · Cited by 31
Wiangkham, T., Duda, J., Haque, M. S., Price, J., & Rushton, A. (2019) · PLOS ONE · doi:10.1371/journal.pone.0215803 · Cited by 22
“To evaluate trial procedures and feasibility of the ABPI in managing acute WADII within the UK insurance private sector to inform the design and sample size requirements for a future definitive RCT. Primary objectives.”
BackgroundInfluential
Metadata
- Authors
- Teerenstra, S., Eldridge, S., Graff, M., de Hoop, E., & Borm, G. F.
- Venue
- Statistics in Medicine
- Publisher
- Wiley
- Published
- 2012-04-11
- Volume
- 31
- Issue
- 20
- Pages
- 2169-2178
- ISSN
- 0277-6715 (ISSN-L)
- 1097-0258
- OpenAlex
- W2139653801
- Cited by
- 89
- References
- 4
- FWCI
- 6.59
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.