[R] mixture distributions

[Jonathan Marchini]

Jobst Landgrebe wrote:
> 
> Dear List,
> 
> I am looking for a possibility to fit a mixture model under R using
> maximum likelihood estimation.
> Venables and Ripley describe a solution working under S+ (in MASS, 3. ed.,
> p. 263) which requires the D system function and deriv3. This solution does not
> seem to be portable to R or at least I do not realise how.
> 
> Is there anyone who
> 
> a) knows how one could make the MASS-method run under R?
> 
> or
> 
> b) has written an EM-algorithm to fit mixture models in R that I could
> use?
> 
> I would be glad to hear from someone.
> 
> Sincerely,
> 
> Jobst

Dear Jobst,

Check out the R package mclust at 

http://www.ci.tuwien.ac.at/R/src/contrib/PACKAGES.html#mclust

It enables you to fit Gaussian Mixture models using the EM algoritm.

Cheers,

Jonathan

> Dr. Jobst Landgrebe
> AG Wurst (Molecular Neurogenetics)
> MPI of Psychiatry
> Kraepelinstr. 2-10
> D-80804 Munich
> phone +49 89 30622626
> fax +49 89 30622642
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> 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
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

-- 
Jonathan L. Marchini,		(home)	jonathan.marchini at balliol.ox.ac.uk
Department of Statistics,	(work)	marchini at stats.ox.ac.uk
University of Oxford,		http://www.stats.ox.ac.uk/~marchini
1 South Parks Road,		Tel: 	+44 1865 272593 (work)	
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._