Iteratively reweighted least squares: A comparison of several single step algorithms for linear models (Q1198981)

During the last 30 years many robust estimators as well as different algorithms for their computation have been suggested in the literature. A very important role among them plays the class of \(\mathcal M\)- estimators. In this interesting paper different known as well as new variants for single step algorithms are studied from a numerical point of view, where the iterations with respect to the parameter vector and the scale parameter alternate. Moreover, results of numerical tests are presented which show numerical efficiency of the studied methods.