Coping with Collinearity

Authors

  • Greg Mason University of Manitoba Research Ltd.

DOI:

https://doi.org/10.3138/cjpe.02.010

Abstract

Collinearity is very common in linear regression. The common methods for diagnosing this disturbance, such as evaluating parameter instability when variables are removed from the specification are only suggestive. Recent developments are reviewed which assist in diagnosing collinear disturbances. These include condition indexes and variance proportions decompositions and are available in a number of statistical packages. Some corrective strategies are also examined. In general, it is not correct to simply drop variables from the specification unless they are redundant to the program logic and underlying theory.

Downloads

Published

1987-03-01

How to Cite

Mason, G. (1987). Coping with Collinearity. Canadian Journal of Program Evaluation, 2(1), 87–93. https://doi.org/10.3138/cjpe.02.010

Issue

Vol. 2 No. 1 (1987): Spring

Section

Articles

License

Copyright (c) 1987 Greg Mason

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Authors contributing to The Canadian Journal of Program Evaluation agree to release their articles under the Creative Commons Attribution-Noncommercial 4.0 (CC-BY-NC) license. This licence allows this work to be copied, distributed, remixed, transformed, and built upon for any purpose provided that appropriate attribution is given, a link is provided to the license, and changes made were indicated.

Authors retain copyright of their work and grant the journal right of first publication.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.