Re: st: Creating a dummy dataset in Stata

[Jeph Herrin <stata@spandrel.net>]

I'm not sure how a 95%CI can be 1 variable, so I will assume you mean 2 variables, the lower and upper bounds.

If you want to be sure your RRs look like RRs:

*---------------------------*
clear
set obs 66
gen ID=_n
gen p=0.5*runiform()+0.25
gen RR=p/(1-p)
gen CIw=RR*runiform()*0.25
gen lowerRR=RR-CIw
gen upperRR=RR+CIw
gen group=ceil(ID/3)
*---------------------------*

hth,
Jeph



On 7/8/2013 9:50 AM, Amal Khanolkar wrote:
> Hi,
>
> I would like to create a dummy dataset in Stata. Say I would like to have a dataset with 4 variables as follows:
>
>
> 1. ID
> 2. Relative risks
> 3. Corresponding 95% CI's for RRs
> 4. A group variable that groups 3 RRs together consecutively from top to bottom.
>
> I know I have 66 IDs and 66 RRs and thus 22 groups (three RRs in each group).
>
> I start with setting the number of observations to 66:
>
> set obs 66
>
> I now have no idea how to enter the RR, 95% CI and the group number for each observation.
>
> Any tips?
>
> Thanks ahead,
>
>
>
> /Amal
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/