Nonparametric Generalized Least Squares in Applied Regression Analysis

19 Pages Posted: 16 Nov 2013

See all articles by Michael O'Hara

Michael O'Hara

St Lawrence University

Christopher F. Parmeter

Virginia Polytechnic Institute & State University

Multiple version iconThere are 2 versions of this paper

Date Written: October 2013

Abstract

This paper compares a nonparametric generalized least squares (NPGLS) estimator to parametric feasible GLS (FGLS) and variants of heteroscedasticity robust standard error estimators (HRSE) in an applied setting. NPGLS consistently estimates the unknown scedastic function and produces more efficient parameter estimates than HRSE. We apply these various approaches for handling heteroscedasticity to data on professor rankings obtained from RateMyProfessors.com. We find that the statistical significance of key variables differs across seven versions of HRSE, leading to different conclusions, and a standard parametric approach to FGLS suffers from misspecification. NPGLS combines the virtues of both of these parametric approaches.

Suggested Citation

O'Hara, Michael and Parmeter, Christopher F., Nonparametric Generalized Least Squares in Applied Regression Analysis (October 2013). Pacific Economic Review, Vol. 18, Issue 4, pp. 456-474, 2013, Available at SSRN: https://ssrn.com/abstract=2355579 or http://dx.doi.org/10.1111/1468-0106.12038

Michael O'Hara

St Lawrence University ( email )

Department of Economics
204 hepburn, 23 Romoda Dr.
Canton, NY 13617
United States

Christopher F. Parmeter

Virginia Polytechnic Institute & State University ( email )

250 Drillfield Drive
Blacksburg, VA 24061
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
0
Abstract Views
323
PlumX Metrics