Double-Length Artificial Regressions

Russell Davidson and James MacKinnon

No 275209, Queen's Institute for Economic Research Discussion Papers from Queen's University - Department of Economics

Abstract: Artificial linear regressions often provide a convenient way to calculate test statistics and estimated covariance matrices. This paper discusses one family of these regressions, called "double-length" because the number of "observations" in the artificial regression is twice the actual number of observations. These double-length regressions can be useful in a wide variety of situations. They are quite easy to calculate, and seem to have good properties when applied to samples of modest size. We first discuss how they are related to the more familiar Gauss-Newton and squared-residuals regressions for nonlinear regression models, then show how they may be used to test for functional form, and finally discuss several other ways in which they may be useful in applied econometric work.

Keywords: Financial; Economics (search for similar items in EconPapers)
Pages: 23
Date: 1987-07
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://ageconsearch.umn.edu/record/275209/files/QUEENS-IER-PAPER-691.pdf (application/pdf)

Related works:
Journal Article: Double Length Artificial Regressions (1988)
Working Paper: Double-Length Artificial Regressions (1987)
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: https://EconPapers.repec.org/RePEc:ags:queddp:275209

DOI: 10.22004/ag.econ.275209

Access Statistics for this paper

More papers in Queen's Institute for Economic Research Discussion Papers from Queen's University - Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by AgEcon Search ().