Permutation tests for stepped-wedge cluster-randomized trials

Permutation tests are useful in stepped-wedge trials to provide robust statistical tests of intervention-effect estimates. However, the permute command does not produce valid tests in this setting because individual observations are not exchangeable. We introduce the swpermute command, which permutes clusters to sequences to maintain exchangeability. The command provides additional functionality for performing analyses of stepped-wedge trials. In particular, we include the withinperiod option, which performs the specified analysis separately in each period of the study with the resulting period-specific intervention-effect estimates combined as a weighted average. We also include functionality to test nonzero null hypotheses to aid in the construction of confidence intervals. Examples of the application of swpermute are given using data from a trial testing the impact of a new tuberculosis diagnostic test on bacterial confirmation of a tuberculosis diagnosis.