On the Impact of the Tests for Serial Correlation Upon the Test of Significance for the Regression Coefficient

Posted: 28 May 2013 Last revised: 30 May 2013

See all articles by Alice Orcutt Nakamura

Alice Orcutt Nakamura

University of Alberta - School of Business

Masao Nakamura

University of British Columbia (UBC) - Sauder School of Business

Date Written: June 29, 1977

Abstract

Monte Carlo methods are used to investigate the relationship between the power of different pretests for autocorrelation, and the Type I error and power of the significance test for a resulting two-stage estimate of the slope parameter in a simple regression. Our results suggest it may be preferable to always transform without pretesting. Moreover we find little room for improvement in the Type I errors and power of two-stage estimators using existing pretests for autocorrelation, compared with the results obtained given perfect knowledge about when to transform (i.e., given a perfect pretest). Rather, researchers should seek better estimators of the transformation parameter itself.

Suggested Citation

Nakamura, Alice Orcutt and Nakamura, Masao, On the Impact of the Tests for Serial Correlation Upon the Test of Significance for the Regression Coefficient (June 29, 1977). Journal of Econometrics, Vol. 7, 1978, University of Alberta School of Business Research Paper No. 2013-253, Available at SSRN: https://ssrn.com/abstract=2270688

Alice Orcutt Nakamura (Contact Author)

University of Alberta - School of Business ( email )

2-32C Business Building
Edmonton, Alberta T6G 2R6
Canada

Masao Nakamura

University of British Columbia (UBC) - Sauder School of Business ( email )

2053 Main Mall
Vancouver, BC V6T 1Z2
Canada
604-822-8434 (Phone)
604-822-8477 (Fax)

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

Paper statistics

Abstract Views
196
PlumX Metrics