[RsR] [R] M-estimator R function question
1. The FORTRAN code of D. Hawkins can be found at ftp://www.stat.umn.edu/pub/fsa/readme.ftp My R interface is only on my local PC and I'll release the MWCD in rrcov. 2. For completeness you can add to the list the exchange and branch and bound algorithms of Jose Agullo. Best regards, Valentin
On 12/5/05, Kristel Joossens <kristel.joossens at econ.kuleuven.be> wrote:
Hello Valentin, Thanks a lot for the information. I will add it! Just one question concerning 3. Can you give me a link where this can be found? Best regards, Kristel Valentin Todorov wrote:
Hi Kristel, a couple of additions to your 'minutes' (Section 2.3 Other): 1. The MATLAB implementation of D. Pe?na & F. Prieto can be found at: http://halweb.uc3m.es/fjp/kur.zip 2. An R implementation of the estimator of D. Olive described in the CSDA paper can be found in http://www.math.siu.edu/olive/rpack.txt - function covmba() 3. I have R interface to some of the FORTRAN programs of Hawkins, but may be only the MWMCD (linear discriminant analysis) is of interest. best regards, Valentin On 12/5/05, Kristel Joossens <kristel.joossens at econ.kuleuven.be> wrote:
Martin Maechler wrote:
"Kjell" == Kjell Konis <konis at stats.ox.ac.uk> on Mon, 5 Dec 2005 10:29:11 +0000 writes:
Kjell> Here is an implementation of the OGK estimator Kjell> completely in R. I haven't touched it for a while Kjell> and I forget how thoroughly I tested it so use it Kjell> with a bit of caution. Kjell> http://www.stats.ox.ac.uk/~konis/pairwise.q excellent! That's exactly what I meant (in my post two hours ago): The general OGK algorithm, but with the flexibility of the main function having arguments for the "building block" functions, so one can use different univariate sigma() or ``weight()'' functions! When we'll start to discuss things along the covRobust() proposal(s) from the "multivariate" working group, we'll also have to think about function name(s) and the returned object ("output"), but I think our student will be able use your function "as is". Thanks a lot, Kjell
Yes, thanks a lot already. Concerning the ``multivariate'' working group, I have put a preliminary Tex and Pdf-file of what we discussed in Treviso online. It can be retreived from: http://www.econ.kuleuven.be/public/ndbae49/R/ If anyone has comments or would like to change/update/add things to the Tex/Pdf-file you can always contact me or send me an updated Tex-file. Best regards, Kristel
Martin.
_______________________________________________ R-SIG-Robust at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-robust
--
__________________________________________ Kristel Joossens Ph.D. Student Research Center ORSTAT K.U. Leuven Naamsestraat 69 Tel: +32 16 326929 3000 Leuven, Belgium Fax: +32 16 326732 E-mail: Kristel.Joossens at econ.kuleuven.be http://www.econ.kuleuven.be/public/ndbae49 Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm _______________________________________________ R-SIG-Robust at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-robust
--
__________________________________________ Kristel Joossens Ph.D. Student Research Center ORSTAT K.U. Leuven Naamsestraat 69 Tel: +32 16 326929 3000 Leuven, Belgium Fax: +32 16 326732 E-mail: Kristel.Joossens at econ.kuleuven.be http://www.econ.kuleuven.be/public/ndbae49 Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm