Hello, I need some basic statistical estimation for current work, but I'm unsure of a correct strategy for data analysis. In simple, given are the series of character state frequencies for n same characters in-group and outgroup:

Ingroup:  0.9  0.8   0.5   0.8  0.7    ...to n-th
Outgroup: 0.01 0.002 0.003 0.05 0.0001 ...to n-th

The goals: 1. estimate the probability that a concurrent observation of high freqs in-group is by chance only (p-value estimation). 2. infer any pairwise or cluster correlations of higher freqs that occur within the ingroup and match the same pattern in the outgroup.

What would be a correct|apt approach to do so? Thanks everyone in advance.