Improved Methods for Making Inferences About Multiple Skipped Correlations

Abstract

A skipped correlation has the advantage of dealing with outliers in a manner that takes into account the overall structure of the data cloud. For p-variate data, $p \ge 2$, there is an extant method for testing the hypothesis of a zero correlation for each pair of variables that is designed to control the probability of one or more Type I errors. And there are methods for the related situation where the focus is on the association between a dependent variable and $p$ explanatory variables. However, there are limitations and several concerns with extant techniques. The paper describes alternative approaches that deal with these issues.