Your problem really isn't well defined. Should
your variables have a normal distribution or
should they be something else? Are you talking
univariate or multivariate distributions?
I don't think your post can be answered usefully
without more detail.
I gather from your email that you are using
Intercooled Stata.
Nick
[email protected]
[email protected]
> I'm trying to run simulation exercises where I have to
> generate variables.
> The only way I know of doing it is by doing -drawnorm- and
> then replacing
> the values one by one - very inefficient.
>
> I also tried -svmat- but if I want to have more than 800
> observations I
> have problems cos I can't generate a matrix with more than 800 rows.
>
> THere must be some simpler ways...
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
