A (k+1)-Decision Two-Stage Selection Procedure for Comparing k Normal Means with a Fixed Known Standard: The Case of Common Unknown Variance.

摘要

A (k+1)-decision two-stage selection procedure is proposed for the problem of comparing k normal means with a fixed known standard when the associated populations have a common unknown variance. None or one of the populations is to be selected, the procedure having the property that (1) with probability at least P0 (specified), no population is to be selected when the largest population mean is sufficiently less than the standard, and (2) with probability at least P1 (specified), the population with the largest population mean is to be selected when that mean is sufficiently greater than its closest competitor and the standard. Tables to implement the procedure are provided. Applications and generalizations are described.