×

A rank-based test for comparison of multidimensional outcomes. (English) Zbl 1392.62322

Summary: For comparison of multiple outcomes commonly encountered in biomedical research, P. Huang et al. [Biometrics 61, No. 2, 532–539 (2005; Zbl 1077.62034)] improved P. C. O’Brien’s [“Procedures for comparing samples with multiple endpoints”, Biometrics 40, 1079–1087 (1984)] rank-sum tests through the replacement of the ad hoc variance by the asymptotic variance of the test statistics. The improved tests control the type I error rate at the desired level and gain power when the differences between the two comparison groups in each outcome variable lie in the same direction; however, they may lose power when the differences are in different directions (e.g., some are positive and some are negative). These tests and the popular Bonferroni correction failed to show important significant differences when applied to compare heart rates from a clinical trial to evaluate the effect of a procedure to remove the cardioprotective solution HTK. We propose an alternative test statistic, taking the maximum of the individual rank-sum statistics, which controls the type I error rate and maintains satisfactory power regardless of the direction of the differences. Simulation studies show the proposed test to be of higher power than other tests in a certain alternative parameter space of interest. Furthermore, when used to analyze the heart rate data, the proposed test yields more satisfactory results.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62G10 Nonparametric hypothesis testing

Citations:

Zbl 1077.62034
PDFBibTeX XMLCite
Full Text: DOI Link