Collinearity and Alternative Estimates

Chapter
Part of the Springer Texts in Statistics book series (STS)

Abstract

Collinearity or multicollinearity refers to the problem in regression analysis of the columns of the model matrix being nearly linear dependent. Ideally, this is no problem at all. There are numerical difficulties associated with the actual computations, but there are no theoretical difficulties. If, however, one has any doubts about the accuracy of the model matrix, the analysis could be in deep trouble.

Keywords

Covariance Shrinkage Lasso 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.Department of Mathematics and Statistics MSC01 11151 University of New MexicoAlbuquerqueUSA

Personalised recommendations