Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes
Abstract Background Cluster randomized trials, which often enroll a small number of clusters, can benefit from constrained randomization, selecting a final randomization scheme from a set of known, balanced randomizations. Previous literature has addressed the suitability of adjusting the analysis f...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12874-025-02465-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585666675867648 |
|---|---|
| author | Amy M. Crisp M. Elizabeth Halloran Matt D. T. Hitchings Ira M. Longini Natalie E. Dean |
| author_facet | Amy M. Crisp M. Elizabeth Halloran Matt D. T. Hitchings Ira M. Longini Natalie E. Dean |
| author_sort | Amy M. Crisp |
| collection | DOAJ |
| description | Abstract Background Cluster randomized trials, which often enroll a small number of clusters, can benefit from constrained randomization, selecting a final randomization scheme from a set of known, balanced randomizations. Previous literature has addressed the suitability of adjusting the analysis for the covariates that were balanced in the design phase when the outcome is continuous or binary. Here we extended this work to time-to-event outcomes by comparing two model-based tests and a newly derived permutation test. A current cluster randomized trial of vector control for the prevention of mosquito-borne disease in children in Mexico is used as a motivating example. Methods We assessed type I error rates and power between simple randomization and constrained randomization using both prognostic and non-prognostic covariates via a simulation study. We compared the performance of a semi-parametric Cox proportional hazards model with robust variance, a mixed effects Cox model, and a permutation test utilizing deviance residuals. Results The permutation test generally maintained nominal type I error—with the exception of the unadjusted analysis for constrained randomization—and also provided power comparable to the two Cox model-based tests. The model-based tests had inflated type I error when there were very few clusters per trial arm. All three methods performed well when there were 25 clusters per trial arm, as in the case of the motivating example. Conclusion For time-to-event outcomes, covariate-constrained randomization was shown to improve power relative to simple randomization. The permutation test developed here was more robust to inflation of type I error compared to model-based tests. Gaining power by adjusting for covariates in the analysis phase was largely dependent on the number of clusters per trial arm. |
| format | Article |
| id | doaj-art-c3d760b31c4f4fb9b04f6841bde616c8 |
| institution | Kabale University |
| issn | 1471-2288 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj-art-c3d760b31c4f4fb9b04f6841bde616c82025-01-26T12:39:32ZengBMCBMC Medical Research Methodology1471-22882025-01-0125111010.1186/s12874-025-02465-wAnalysis methods for covariate-constrained cluster randomized trials with time-to-event outcomesAmy M. Crisp0M. Elizabeth Halloran1Matt D. T. Hitchings2Ira M. Longini3Natalie E. Dean4Department of Biostatistics, University of FloridaDepartment of Biostatistics, University of WashingtonDepartment of Biostatistics, University of FloridaDepartment of Biostatistics, University of FloridaDepartment of Biostatistics and Bioinformatics, Emory UniversityAbstract Background Cluster randomized trials, which often enroll a small number of clusters, can benefit from constrained randomization, selecting a final randomization scheme from a set of known, balanced randomizations. Previous literature has addressed the suitability of adjusting the analysis for the covariates that were balanced in the design phase when the outcome is continuous or binary. Here we extended this work to time-to-event outcomes by comparing two model-based tests and a newly derived permutation test. A current cluster randomized trial of vector control for the prevention of mosquito-borne disease in children in Mexico is used as a motivating example. Methods We assessed type I error rates and power between simple randomization and constrained randomization using both prognostic and non-prognostic covariates via a simulation study. We compared the performance of a semi-parametric Cox proportional hazards model with robust variance, a mixed effects Cox model, and a permutation test utilizing deviance residuals. Results The permutation test generally maintained nominal type I error—with the exception of the unadjusted analysis for constrained randomization—and also provided power comparable to the two Cox model-based tests. The model-based tests had inflated type I error when there were very few clusters per trial arm. All three methods performed well when there were 25 clusters per trial arm, as in the case of the motivating example. Conclusion For time-to-event outcomes, covariate-constrained randomization was shown to improve power relative to simple randomization. The permutation test developed here was more robust to inflation of type I error compared to model-based tests. Gaining power by adjusting for covariates in the analysis phase was largely dependent on the number of clusters per trial arm.https://doi.org/10.1186/s12874-025-02465-wClinical trial designCluster-randomizedConstrained randomizationTime-to-eventPermutation test |
| spellingShingle | Amy M. Crisp M. Elizabeth Halloran Matt D. T. Hitchings Ira M. Longini Natalie E. Dean Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes BMC Medical Research Methodology Clinical trial design Cluster-randomized Constrained randomization Time-to-event Permutation test |
| title | Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes |
| title_full | Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes |
| title_fullStr | Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes |
| title_full_unstemmed | Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes |
| title_short | Analysis methods for covariate-constrained cluster randomized trials with time-to-event outcomes |
| title_sort | analysis methods for covariate constrained cluster randomized trials with time to event outcomes |
| topic | Clinical trial design Cluster-randomized Constrained randomization Time-to-event Permutation test |
| url | https://doi.org/10.1186/s12874-025-02465-w |
| work_keys_str_mv | AT amymcrisp analysismethodsforcovariateconstrainedclusterrandomizedtrialswithtimetoeventoutcomes AT melizabethhalloran analysismethodsforcovariateconstrainedclusterrandomizedtrialswithtimetoeventoutcomes AT mattdthitchings analysismethodsforcovariateconstrainedclusterrandomizedtrialswithtimetoeventoutcomes AT iramlongini analysismethodsforcovariateconstrainedclusterrandomizedtrialswithtimetoeventoutcomes AT natalieedean analysismethodsforcovariateconstrainedclusterrandomizedtrialswithtimetoeventoutcomes |