Maybe specifying a non-PSD covariance/corr matrix? e.g.
drawnorm x1-x3, clear seed(1) n(100) corr(1,.9,.8 \ .9,1,-.8 \ .8,-.8, 1)
On Sun, Sep 27, 2009 at 9:50 AM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> What is the error message? This works w/o a hitch:
>
> **************
> clear*
> drawnorm x y, n(10000) corr(1, 0.9 \ 0.9, 1) cstorage(full)
> corr
> **************
>
>
> HTH
> Martin
>
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of
> [email protected]
> Sent: Freitag, 25. September 2009 17:22
> To: [email protected]
> Subject:
>
> Hi all,
> Can anyone please tell me reason(s)why I could no longer generate sample
> data sets using drawnorm command simply because the specified covariate-
> outcome correlation is more than 0.5.
> I did not have any problem with correlation of less than or equal to 0.5.
> Please I await your responses.
> Thanks.
> Emmanuel
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/