1

I am helping with a paper where a co-author got Spearman correlations between each of 6 variables.

I've seen that permutation is likely the best way to increase power for these (if I'm understanding it correctly), but is a Bonferroni correction a valid way to do this?

I don't have access to the data, and the person working on this is not a statistician, so I'm trying to offer an alternative to just spitting out 30+ correlations without multiple testing corrections (which is the current state of things).

Gaius Augustus
  • 153
  • 5
  • Have a look [here](http://stats.stackexchange.com/questions/225937/linear-mixed-effects-model-and-multiplicity-issue-and-adjusting-for-p-values/226215#226215). Does this help? – Stefan Jul 31 '16 at 05:16

0 Answers0