Multivariate data

What a 1997 JSS paper with interactive graphics looked like then and still does

In 1997, I wrote a paper that was accepted for the newly fledged Journal of Statistical Software. That article is still available at It looks nothing like the original published paper. Papers today are only published in pdf format, unlike the original which were delivered as html, with pdf being a secondary format o help readers who preferred a printed copy. My paper was titled “Calibrate your to Recognise High-Dimensional Shapes from their Low-Dimensional Projections”.

How to use a tour to check if your model suffers from multicollinearity

Multicollinearity This was one of the comments from a recent review of a paper: As you note in the paper, it seems likely that there are still issues with multi-collinearity Multicollinearity means that the observations are co-linear in some combination of the variables. This has been relaxed in practice to mean substantial association between explanatory variables. When your explanatory variables have substantial association between them, it means that you don’t have a stable base on which to build a model.