On Tue, 9 Feb 1999, Peter ridall wrote:
> Has anybody written or located a robust verion of Var(X)?
I'm not sure what you mean by `robust', precisely, but one of
cov.trob in package MASS in the VR bundle
cov.rob in package lqs (part of the pre-release of 0.63.3) and
also available as an add-on package in the Windows collection and at
http://www.stats.ox.ac.uk/pub/R
will probably do what you want.
Robustness for a multivariate problem has several definitions; cov.trob has
high efficiency near the normal, cob.rob has high breakdown point. For
those familiar with S-PLUS, cov.rob supersedes cov.mve and cov.mcd (and was
written to replace those in V&R3), and has wrappers to emulate them.
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272860 (secr)
Oxford OX1 3TG, UK Fax: +44 1865 272595
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._