Hypothesis Testing of Population Percentiles via the Wald Test with Bootstrap Variance Estimates  

作　　者：William D. Johnson Jacob E. Romer William D. Johnson;Jacob E. Romer(Department of Biostatistics, Pennington Biomedical Research Center, Louisiana State University, Baton Rouge, LA, USA)

机构地区：[1]Department of Biostatistics, Pennington Biomedical Research Center, Louisiana State University, Baton Rouge, LA, USA

出　　处：《Open Journal of Statistics》2016年第1期14-24,共11页统计学期刊（英文）

摘　　要：Testing the equality of percentiles (quantiles) between populations is an effective method for robust, nonparametric comparison, especially when the distributions are asymmetric or irregularly shaped. Unlike global nonparametric tests for homogeneity such as the Kolmogorv-Smirnov test, testing the equality of a set of percentiles (i.e., a percentile profile) yields an estimate of the location and extent of the differences between the populations along the entire domain. The Wald test using bootstrap estimates of variance of the order statistics provides a unified method for hypothesis testing of functions of the population percentiles. Simulation studies are conducted to show performance of the method under various scenarios and to give suggestions on its use. Several examples are given to illustrate some useful applications to real data.Testing the equality of percentiles (quantiles) between populations is an effective method for robust, nonparametric comparison, especially when the distributions are asymmetric or irregularly shaped. Unlike global nonparametric tests for homogeneity such as the Kolmogorv-Smirnov test, testing the equality of a set of percentiles (i.e., a percentile profile) yields an estimate of the location and extent of the differences between the populations along the entire domain. The Wald test using bootstrap estimates of variance of the order statistics provides a unified method for hypothesis testing of functions of the population percentiles. Simulation studies are conducted to show performance of the method under various scenarios and to give suggestions on its use. Several examples are given to illustrate some useful applications to real data.

关 键 词：BOOTSTRAP Hypothesis Testing Nonparametric Methods Percentile Profiles Wald Test 

分 类 号：O17[理学—数学]