Re: [R] Multivariate skew-t cdf

From: Konrad Banachewicz <>
Date: Tue 06 Jun 2006 - 23:52:20 EST

> Thanks to Spencer Graves for provinding this clarification about pmst.
> As the author of pmst, I was really the one expected to answer the
> query, but I was on travel in the last two weeks and did not read
> this query.
> As a complement to what already explained, the reason of the sharp change
> from k=19 to k=20 is as follows: pmst (package sn) calls pmt (package
> mnormt) with k increased by 1, and pmt calls a Fortran routine (written by
> Alan Genz), which issues an error if k>20 or k<1. Hence, the effective
> maximum number of dimensions allowed by pmst is 19.

Ok, thanks a lot to both of You for help - with Your explanations, You really clarified my view of the
problem (and saved me a lot of time I would've spent on digging through my own code).

best wishes,
Konrad Banachewicz

best wishes,
> Adelchi Azzalini
> > Also, have you asked about this directly to the maintainers of
> the
> > "sn", "mnormt" and "mvtnorm" packages? They might have other
> suggestions.
> >
> > Hope this helps.
> > Spencer Graves
> --
> "We are what we pretend to be, so we must be careful about what we pretend
> to be"
> Kurt Vonnegut Jr. "Mother Night"

        [[alternative HTML version deleted]] mailing list PLEASE do read the posting guide! Received on Wed Jun 07 00:00:08 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Wed 07 Jun 2006 - 02:10:36 EST.

Mailing list information is available at Please read the posting guide before posting to the list.