Event

CRXO designs are not uncommon in public health research and bounded discrete endpoints, such as pain scales, are common.  The justification of sample size (i.e. the number of clusters, periods and individuals) is generally based on power calculations that assume continuous-scale, normally-distributed, primary endpoints.  In this talk, various approaches are reviewed and some simulation-based results are reported for the power of a conventional test procedure when it is “misapplied” to a bounded discrete endpoint.