Peter Dalgaard BSA <[EMAIL PROTECTED]> writes:
> This was discussed here in October. For the multivariate T you can use
>
> rmvt <- function(corr,df)
> rmvnorm(n,sigma=corr)/sqrt(rchisq(n,df)/df)
>
> (R.Koenker, correcting my suggestion). I believe rmvnorm came from the
> mvtnorm package but there's also mvrnorm in library(MASS).
... and of course Torsten in the meantime added that one to the
mvtnorm package as Jerome points out. Doh!
-p
--
O__ ---- Peter Dalgaard Blegdamsvej 3
c/ /'_ --- Dept. of Biostatistics 2200 Cph. N
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~~~~~~~~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907
______________________________________________
[EMAIL PROTECTED] mailing list
http://www.stat.math.ethz.ch/mailman/listinfo/r-help
