Suppose I have two independent samples. How can I test if the two samples have been drawn from the same distribution using a permutation test? The sample sizes are equal. The population distributions are unknown.
Asked
Active
Viewed 36 times
0
-
You need to start with what kinds of differences you want most to pick up. If you're just after *any* kind of difference in distribution, the usual two sample test statistics (such as the Kolmogorov-Smirnov, for example) might be a suitable statistic for a permutation test.. – Glen_b Jul 21 '15 at 09:40
-
I wrote my answer to the duplicate specifically to address future related questions like this one. – whuber Jul 21 '15 at 14:54