Re: Multivariate student t: normalization in mvtrnd

[Iñigo Urteaga]

Hi Arno,

Thanks a lot for clarifying that Octave's mvtrnd normalizes the
covariance matrix into the correlation matrix just for compatibility
purposes with Matlab. I understand that this is design criteria and I
don't expect it to change. Nevertheless, what is the reasoning behind
not using the covariance but the correlation matrix? Is there any
advantage?

Finally, would it make any sense to expand mvtrnd's help a little to
clarify this point for other users? I spent some time trying to figure
this out, so I consider it might be helpful for others. If you agree,
I am willing to help.

Thank you all in the Octave community for your help.

Iñigo

On Tue, Nov 27, 2012 at 2:52 AM, Arno Onken <address@hidden> wrote:
> You are right in the sense that we could generate multivariate t samples
> with arbitrary covariance matrix and without a subsequent rescaling by
> removing the normalization step.