The Use of Permutation Tests for the Analysis of Parallel and Stepped-wedge Cluster-randomized Trials

Overview

Journal Stat Med

Publisher Wiley

Specialty Public Health

Date 2017 May 3

PMID 28464567

Citations 25

Authors

Rui Wang

Victor de Gruttola

Affiliations

Soon will be listed here.

Abstract

We investigate the use of permutation tests for the analysis of parallel and stepped-wedge cluster-randomized trials. Permutation tests for parallel designs with exponential family endpoints have been extensively studied. The optimal permutation tests developed for exponential family alternatives require information on intraclass correlation, a quantity not yet defined for time-to-event endpoints. Therefore, it is unclear how efficient permutation tests can be constructed for cluster-randomized trials with such endpoints. We consider a class of test statistics formed by a weighted average of pair-specific treatment effect estimates and offer practical guidance on the choice of weights to improve efficiency. We apply the permutation tests to a cluster-randomized trial evaluating the effect of an intervention to reduce the incidence of hospital-acquired infection. In some settings, outcomes from different clusters may be correlated, and we evaluate the validity and efficiency of permutation test in such settings. Lastly, we propose a permutation test for stepped-wedge designs and compare its performance with mixed-effect modeling and illustrate its superiority when sample sizes are small, the underlying distribution is skewed, or there is correlation across clusters. Copyright © 2017 John Wiley & Sons, Ltd.

Citing Articles

A review of current practice in the design and analysis of extremely small stepped-wedge cluster randomized trials.

Tong G, Nevins P, Ryan M, Davis-Plourde K, Ouyang Y, Pereira Macedo J Clin Trials. 2024; 22(1):45-56.

PMID: 39377196 PMC: 11810615. DOI: 10.1177/17407745241276137.

Robust analysis of stepped wedge trials using composite likelihood models.

Voldal E, Kenny A, Xia F, Heagerty P, Hughes J Stat Med. 2024; 43(17):3326-3352.

PMID: 38837431 PMC: 11257102. DOI: 10.1002/sim.10120.

Maintaining the validity of inference from linear mixed models in stepped-wedge cluster randomized trials under misspecified random-effects structures.

Ouyang Y, Taljaard M, Forbes A, Li F Stat Methods Med Res. 2024; 33(9):1497-1516.

PMID: 38807552 PMC: 11499024. DOI: 10.1177/09622802241248382.

Opportunistic Treatment of Hepatitis C Infection Among Hospitalized People Who Inject Drugs (OPPORTUNI-C): A Stepped Wedge Cluster Randomized Trial.

Midgard H, Malme K, Pihl C, Berg-Pedersen R, Tanum L, Klundby I Clin Infect Dis. 2023; 78(3):582-590.

PMID: 37992203 PMC: 10954343. DOI: 10.1093/cid/ciad711.

Permutation-based multiple testing corrections for -values and confidence intervals for cluster randomized trials.

Watson S, Akinyemi J, Hemming K Stat Med. 2023; 42(21):3786-3803.

PMID: 37340888 PMC: 10962558. DOI: 10.1002/sim.9831.

References

Murray D, Hannan P, Pals S, McCowen R, Baker W, Blitstein J . A comparison of permutation and mixed-model regression methods for the analysis of simulated data in the context of a group-randomized trial. Stat Med. 2005; 25(3):375-88. DOI: 10.1002/sim.2233. View

. Community Intervention Trial for Smoking Cessation (COMMIT): summary of design and intervention. COMMIT Research Group. J Natl Cancer Inst. 1991; 83(22):1620-8. DOI: 10.1093/jnci/83.22.1620. View

Stephens A, Tchetgen Tchetgen E, de Gruttola V . FLEXIBLE COVARIATE-ADJUSTED EXACT TESTS OF RANDOMIZED TREATMENT EFFECTS WITH APPLICATION TO A TRIAL OF HIV EDUCATION. Ann Appl Stat. 2014; 7(4):2106-2137. PMC: 3935423. DOI: 10.1214/13-AOAS679. View

Jacobowitz H, Metzler S . Geometric Sensitivity of a Pinhole Collimator. Int J Math Math Sci. 2014; 2010:915958. PMC: 3898866. DOI: 10.1155/2010/915958. View

Wang R, Lagakos S, Gray R . Testing and interval estimation for two-sample survival comparisons with small sample sizes and unequal censoring. Biostatistics. 2010; 11(4):676-92. PMC: 2950789. DOI: 10.1093/biostatistics/kxq021. View

Wang R, Schoenfeld D, Hoeppner B, Evins A . Detecting treatment-covariate interactions using permutation methods. Stat Med. 2015; 34(12):2035-47. PMC: 4420688. DOI: 10.1002/sim.6457. View

Brookmeyer R, Chen Y . Person-time analysis of paired community intervention trials when the number of communities is small. Stat Med. 1998; 17(18):2121-32. DOI: 10.1002/(sici)1097-0258(19980930)17:18<2121::aid-sim907>3.0.co;2-s. View

Wang R, Lagakos S . Inference after variable selection using restricted permutation methods. Can J Stat. 2010; 37(4):625-644. PMC: 2848082. DOI: 10.1002/cjs.10039. View

Hussey M, Hughes J . Design and analysis of stepped wedge cluster randomized trials. Contemp Clin Trials. 2006; 28(2):182-91. DOI: 10.1016/j.cct.2006.05.007. View

10.

Prague M, Wang R, Stephens A, Tchetgen Tchetgen E, DeGruttola V . Accounting for interactions and complex inter-subject dependency in estimating treatment effect in cluster-randomized trials with missing outcomes. Biometrics. 2016; 72(4):1066-1077. PMC: 5055852. DOI: 10.1111/biom.12519. View

11.

Huskins W, Huckabee C, OGrady N, Murray P, Kopetskie H, Zimmer L . Intervention to reduce transmission of resistant bacteria in intensive care. N Engl J Med. 2011; 364(15):1407-18. PMC: 3410743. DOI: 10.1056/NEJMoa1000373. View

12.

Zimmerman D . Statistical significance levels of nonparametric tests biased by heterogeneous variances of treatment groups. J Gen Psychol. 2000; 127(4):354-64. DOI: 10.1080/00221300009598589. View

13.

Gail M, Mark S, Carroll R, Green S, Pee D . On design considerations and randomization-based inference for community intervention trials. Stat Med. 1996; 15(11):1069-92. DOI: 10.1002/(SICI)1097-0258(19960615)15:11<1069::AID-SIM220>3.0.CO;2-Q. View

14.

Gail M, Byar D, Pechacek T, Corle D . Aspects of statistical design for the Community Intervention Trial for Smoking Cessation (COMMIT). Control Clin Trials. 1992; 13(1):6-21. DOI: 10.1016/0197-2456(92)90026-v. View