# About help on 'mahalanobis' Classic List Threaded 2 messages Reply | Threaded
Open this post in threaded view
|

## About help on 'mahalanobis'

 Hi, help on 'mahalanobis' (in the stats package in Rv2.2.0) now says: "Description:       Returns the Mahalanobis distance of all rows in 'x' and the vector       mu='center' with respect to Sigma='cov'. This is (for vector 'x')       defined as                   D^2 = (x - mu)' Sigma^{-1} (x - mu)" It does return D^2 as written.  However, would the text be more clear if it says "Returns the _squared_ Mahalanobis distance D^2..." instead?  If so, then text in the example code, e.g. "##- Here, D^2 = usual Euclidean distances" and the title of the first plot will also have to be updated. Compare this with what dist() in the same package returns.  When asking for the Equlidean distance (matrix) between rows in a matrix, we get D not D^2, e.g. dist(c(1,3)) == 2. Cheers Henrik ______________________________________________ [hidden email] mailing list https://stat.ethz.ch/mailman/listinfo/r-helpPLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

## Re: About help on 'mahalanobis'

 >>>>> "HenrikB" == Henrik Bengtsson <[hidden email]> >>>>>     on Wed, 14 Dec 2005 17:05:32 +1100 writes:     HenrikB> Hi,     HenrikB> help on 'mahalanobis' (in the stats package in Rv2.2.0) now says:     HenrikB> "Description:     HenrikB> Returns the Mahalanobis distance of all rows in 'x' and the vector     HenrikB> mu='center' with respect to Sigma='cov'. This is (for vector 'x')     HenrikB> defined as     HenrikB> D^2 = (x - mu)' Sigma^{-1} (x - mu)"     HenrikB> It does return D^2 as written.  However, would the     HenrikB> text be more clear if it says "Returns the     HenrikB> _squared_ Mahalanobis distance D^2..." instead?  If     HenrikB> so, then text in the example code, e.g. "##- Here,     HenrikB> D^2 = usual Euclidean distances" and the title of     HenrikB> the first plot will also have to be updated. Indeed, thank you! Committed {even to R-beta}.     HenrikB> Compare this with what dist() in the same package     HenrikB> returns.  When asking for the Equlidean distance     HenrikB> (matrix) between rows in a matrix, we get D not     HenrikB> D^2, e.g. dist(c(1,3)) == 2. ______________________________________________ [hidden email] mailing list https://stat.ethz.ch/mailman/listinfo/r-helpPLEASE do read the posting guide! http://www.R-project.org/posting-guide.html