Hi, there: This is a bit off-topic but I try to do it in R so I put it here: I have 31 samples from a population of genes, and each sample contains a pair of gene lists, with different lengths and the intersection between the two lists also varies. I want to test my hypothesis by creating a null hypothesis for this population. Since the distribution for the length and the distribution for the intersection size do not follow any known distribution, I think I need to use sample with replacement to simulate those "parameters". And use the parameters to permutate genes; but I am not very sure if it is alll right. BTW, is there any general package or I just need "sample()" to do that? (just tried to make my question on-topic:) thanks, -- Weiwei Shi, Ph.D Research Scientist GeneGO, Inc. "Did you always know?" "No, I did not. But I believed..." ---Matrix III