Re: st: corr2data

[Martin Weiss <martin.weiss@uni-tuebingen.de>]

You can get rid of the negatives after -drawnorm- but there is no way  
the mean stays constant then.

********
clear*
set seed 12345
matrix C = (1, .5 \ .5, 1)
drawnorm x y, n(1000) corr(C)

*let`s take a look
su,d

*kill the negative values
su y, mean
replace y=y-r(min)
su x,mean
replace x=x-r(min)

*sd the same, mean shifted upwards
su,d
*********

You could also plug in a mean of 10 and a sd of 1 into -drawnorm-, and  
there is very little chance you will get any negatives, but I suspect  
you have something different in mind.

HTH
Martin


Quoting Hema Mistry <mistry_hema@hotmail.co.uk>:


> Dear all,
>
> Does anyone know with the corr2data command whether you can set a   
> lower and upper limit whilst keeping the same mean and sd?
>
> Also is there another command similar to corr2data (drawnorm also   
> has the same problems) which won't give me negative values and   
> produces the same mean and SD, but keeping the original values and   
> expanding on these values.
>
> Thanks
>
> Hema
>
> _________________________________________________________________
> Make a mini you and download it into Windows Live Messenger
> http://clk.atdmt.com/UKM/go/111354029/direct/01/
> *
> *   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/



*
*   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/