Al Feeders asks:
> -----Original Message-----
> From: Ad Feelders [mailto:ad@cs.uu.nl]
> Sent: Wednesday, May 29, 2002 12:17 AM
> To: s-news@lists.biostat.wustl.edu
> Subject: [S] random draws from multivariate normal
>
> Dear list,
>
> Can anybody give me pointers for the following problem?
>
> I would like to generate random draws from a high (say 25) dimensional
> multivariate normal distribution,
> where the covariance/correlation matrix should be generated at random as
> well. Since the covariance matrix
> should be positive definite, a fully random matrix is not appropriate.
>
> Is there any possibility if generating a "random" positive definite
> covariance matrix?
> Any pointers to relevant literature are welcome.
[WNV] If your problem really is so unstructured this is very
simple:
rpdsm <- crossprod(matrix(rnorm(5*5), 5, 5))
will do it. This gives you a standard 5x5 Wishart matrix with 5 df.
Variations are clearly possible.
> Thanks for your help.
>
> -Ad Feelders
>
> --------------------------------------------------------------------------
> -
> Ad Feelders
> Universiteit Utrecht
> Institute of Information & Computing Sciences
> PO Box 80089
> 3508 TB Utrecht
> The Netherlands
> ad@cs.uu.nl
> Phone: +31 30 2533176
>
> --------------------------------------------------------------------
> This message was distributed by s-news@lists.biostat.wustl.edu. To
> unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with
> the BODY of the message: unsubscribe s-news
|