Premium
A Bayesian analysis of small n sequential multiple assignment randomized trials (snSMARTs)
Author(s) -
Wei Boxian,
Braun Thomas M.,
Tamura Roy N.,
Kidwell Kelley M.
Publication year - 2018
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.7900
Subject(s) - confidence interval , estimator , statistics , randomized controlled trial , poisson distribution , bayesian probability , mean squared error , inference , stage (stratigraphy) , square root , bayesian inference , credible interval , computer science , mathematics , medicine , artificial intelligence , paleontology , biology , geometry
Designing clinical trials to study treatments for rare diseases is challenging because of the limited number of available patients. A suggested design is known as the small n sequential multiple assignment randomized trial (snSMART), in which patients are first randomized to one of multiple treatments (stage 1). Patients who respond to their initial treatment continue the same treatment for another stage, while those who fail to respond are rerandomized to one of the remaining treatments (stage 2). The data from both stages are used to compare the efficacy between treatments. Analysis approaches for snSMARTs are limited, and we propose a Bayesian approach that allows for borrowing of information across both stages. Through simulation, we compare the bias, root‐mean‐square error, width, and coverage rate of 95 % confidence/credible interval of estimators from of our approach to estimators produced from (i) standard approaches that only use the data from stage 1, and (ii) a log‐Poisson model using data from both stages whose parameters are estimated via generalized estimating equations. We demonstrate the root‐mean‐square error and width of 95 % confidence/credible intervals of our estimators are smaller than the other approaches in realistic settings, so that the collection and use of stage 2 data in snSMARTs provide improved inference for treatments of rare diseases.