A description of a system of subroutines to compute solutions to the iteratively reweighted least squares problem is presented. The weights are determined from the data and linear fit and are computed as functions of the scaled residuals. Iteratively reweighted least squares is a part of robust...

A brief discussion of recent methods using the Hat Matrix for identifying leverage points, and clustering techniques for finding groups of data points is presented. The problem of identifying leverage groups is addressed, and a heuristic algorithm for identifying both leverage points and...