摘要：The determination of two groups of observations with respect to a simple cutpoint of a predictor is a common problem in medical statistics. For example, the distinction of a low and high risk group of patients is of special interest. The selection of a cutpoint in the predictor leads to a multiple testing problem, cf. Figure 1. This has to be taken into account when the effect of the selected cutpoint is evaluated. Maximally selected rank statistics can be used for estimation as well as evaluation of a simple cutpoint model. We show how this problems can be treated with the maxstat package and illustrate the usage of the package by gene expression profiling data.
