Pearson M-Estimators in Regression Analysis

Paper number: 95/17

Paper date: October 1995

Year: 1995

Paper Category: Discussion Paper


Michael A Magdalinos*
Athens University of Economics and Business


George P Mitsopoulos
Athens University of Economics and Business


This paper derives and adaptive partial solution for the maximum likelihood normal equations of a regression, under the assumption that the errors belong to the Pearson family. This estimator can be "robustified" producing a M-estimator with satisfactory efficiency for a wider range of error distributions. Monte-Carlo evidence on the finite sample properties of the estimates is reported. The computational requirements are very modest: all the proposed improvements can be computed with the help of an auxilliary regression.

JEL Classification numbers: C13.
Keywords: Pearson family, Regression, M-estimators, Non-normal Errors.

*Visiting Professor, Department of Economics, University of Exeter, Amory Building, Rennes Drive, Exeter, Devon, England. EX4 4RJ.