Abstract
A Bayesian group sequential design is proposed that performs survival comparisons within patient subgroups in randomized trials where treatment–subgroup interactions may be present. A latent subgroup membership variable is assumed to allow the design to adaptively combine homogeneous subgroups, or split heterogeneous subgroups, to improve the procedure’s within-subgroup power. If a baseline covariate related to survival is available, the design may incorporate this information to improve subgroup identification while basing the comparative test on the average hazard ratio. General guidelines are provided for calibrating prior hyperparameters and design parameters to control the overall Type I error rate and optimize performance. Simulations show that the design is robust under a wide variety of different scenarios. When two or more subgroups are truly homogeneous but differ from the other subgroups, the proposed method is substantially more powerful than tests that either ignore subgroups or conduct a separate test within each subgroup. Supplementary materials for this article are available online.
Original language | English (US) |
---|---|
Pages (from-to) | 322-334 |
Number of pages | 13 |
Journal | Journal of the American Statistical Association |
Volume | 116 |
Issue number | 533 |
DOIs | |
State | Published - 2020 |
Keywords
- Bayesian analysis
- Group sequential
- Piecewise exponential model
- Randomized comparative trial
- Response heterogeneity
- Survival comparison
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
MD Anderson CCSG core facilities
- Biostatistics Resource Group