Multiple Comparison for Checking Correlations among Several Normal Random Variables
Tsunehisa Imada, Hideyuki Douke · Institutional Repositories DataBase (IRDB) · 2015
In this study we discuss a multiple comparison for checking correlations among several normal random variables.Specifically, we construct two kinds of multiple comparison procedures using t-distribution based on sample correlation coefficient for pairwise comparison.One is a single step procedure based on Bonferroni's inequality.The other is a sequentially rejective step down procedure based on Holm's method.We compare two procedures in terms of the power of the test in a simulation study.Finally, we give an example to illustrate our procedures.