Best Practices in Quantitative Methods by Osborne Jason W

Author:Osborne, Jason W. [Osborne, Jason W.]
Language: eng
Format: epub
ISBN: 9781483333052
Publisher: SAGE Publications
Published: 2007-11-13T00:00:00+00:00

Robust Regression Estimators

In some cases, it might suffice to fit the model

Y = β0 + β1X1+ … + βpXp+ε.

(4)

What is needed now are estimators that avoid misleading results or poor power due to outliers or heteroscedasticity. Numerous alternatives to the ordinary least squares estimator have been proposed, many of which can have a considerable practical advantage. Even under normality, several estimators can have substantially smaller standard errors than the least squares estimator when there is heteroscedasticity. Space limitations make it impossible to describe all of these estimators in great detail. A fairly comprehensive summary can be found in Wilcox (2005b), but even now, not all estimators are covered. The goal here is to outline a few estimators and comment on their relative merits.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.