Comparison Between Two-Sample Adaptive Tests And Traditional Tests Under Symmetric And Skewed Distributions For Location Problem

The most familiar test for two sample location problem is the parametric t test and non parametric wilcoxon test provided the parent distribution is normal. But if the data set follows a skewed distribution then these two tests may give an inaccurate result. In this paper it is tried to give a solution to this problem by the use of adaptive tests. Power comparisons are made here between t test, wilcoxon test and proposed adaptive tests by monte carlo simulation method.