Criterion Mixing Lack of Fit and Multicolinearity for Variable Selection in Regression

Jean-Daniel Rolle

Working Papers from Ecole des Hautes Etudes Commerciales, Universite de Geneve-

Abstract: We describe in this paper a method allowing to order submodels in linear regression. A real function is attached to each submodel, allowing to graphically compare and order them. Our procedure defines an objective function depending on two factors (lack of fit and multicolinearity) with the property that the minimum of this function over subsets of the regressors determines the "best" such subset of variables. The latter will be found by systematically examining all possible subsets having at least two regressors. The method is built in such a way that it allows a graphical inspection of the submodels. Although it is presented here only in the framework of linear regression with a single, continuous, response variable, the procedure may be extended in a natural way to more general regression models. Simulation and implementation on various data sets gave very satisfying results

Keywords: REGRESSION ANALYSIS; ECONOMETRICS; ECONOMIC MODELS (search for similar items in EconPapers)
JEL-codes: C00 C10 C20 C50 (search for similar items in EconPapers)
Pages: 15 pages
Date: 1999
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
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:fth:ehecge:99.11

Access Statistics for this paper

More papers in Working Papers from Ecole des Hautes Etudes Commerciales, Universite de Geneve- Suisse; Ecole des Hautes Etudes Commerciales, Universite de Geneve, faculte des SES. 102 Bb. Carl-Vogt CH - 1211 Geneve 4, Suisse. Contact information at EDIRC.
Bibliographic data for series maintained by Thomas Krichel ().