Collinearity diagnostics are widely used, but the typical tabular output used in almost all software makes it hard to tell what to look for and how to understand the results. We describe a simple improvement to the standard tabular display, a graphic rendition of the salient information as a "tableplot," and graphic displays designed to make the information in these diagnostic methods more readily understandable. In addition, we propose a visualization of the contributions of the predictors to collinearity through a "collinearity biplot," which is simultaneously a biplot of the smallest dimensions of the correlation matrix of the predictors, R XX, and the largest dimensions of R XX -1, on which the standard collinearity diagnostics are based.

, , , , , ,
doi.org/10.1198/tast.2009.0012
Journal of the American Statistical Association
Sprott School of Business

Friendly, M. (Michael), & Kwan, E. (2009). Where's waldo? Visualizing collinearity diagnostics. Journal of the American Statistical Association, 63(1), 56–65. doi:10.1198/tast.2009.0012