Artificial Regressions

Russell Davidson and James MacKinnon ()

No 978, Working Papers from Queen's University, Department of Economics

Abstract: Associated with every popular nonlinear estimation method is at least one "artificial" linear regression. We define an artificial regression in terms of three conditions that it must satisfy. Then we show how artificial regressions can be useful for numerical optimization, testing hypotheses, and computing parameter estimates. Several existing artificial regressions are discussed and are shown to satisfy the defining conditions, and a new artificail regression for regression models with heteroskedasticity of unknown form is introduced.

Keywords: Gauss-Newton Regression; Specification Test; Heteroskedasticity (search for similar items in EconPapers)
JEL-codes: C12 (search for similar items in EconPapers)
Date: Written

Published in B. Baltagi, Companion to Theoretical Econometrics, Blackwell, 2001

Downloads: (external link)
http://www.econ.queensu.ca/working_papers/papers/qed_wp_978.pdf First version 1999 (application/pdf)

Related works:
Working Paper: Artificial Regressions (1999)
Working Paper: Artificial Regressions (2001)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:qed:wpaper:978

Access Statistics for this paper

More papers in Working Papers from Queen's University, Department of Economics
Contact information at EDIRC.
Series data maintained by Mark Babcock ().