I think you need to join the "standard" data set to your children/adolsecent data set by age (you may want to code age, e.g., 61, 62, 63...) and sex.
Then: underwt=1 if bmi < p5
Elizabeth
>>> On 6/25/2007 at 2:44 PM, in message
<[email protected]>, "Visintainer, Paul"
<[email protected]> wrote:
> I have a dataset of about 1000 children and adolescents all of whom have
> BMIs. I want to generate 3 new variables: underwt < 5th %ile; overwt >
> 85th %ile; obese > 95th %ile, based on their age and sex (I give a
> synopsis of one of the command below).
>
> gen underwt = 1 if sex==[0 or 1] & agemo== [57.5 mos to 215 mos]
> & bmi < [a specific value]
>
>
> My problem is that the unique BMI cutpoints based on age and sex (the
> "specific value" in the command above--more than 400 of them), are in
> another dataset. The format of the dataset with the BMI standards looks
> like:
>
> Sex Agemo P5 P85 P95
> 1 61.5 13.82664746 16.84600319 17.96602144
> 1 62.5 13.81537489 16.85300198 17.99561523
> 1 63.5 13.8047237 16.86173124 18.02763543
> 1 64.5 13.79469004 16.87216519 18.06201396
> 1 65.5 13.78526882 16.88428085 18.09868317
> 1 66.5 13.77645627 16.89805459 18.13757754
> . . .
>
> I don't want to have to type in each unique BMI standard. Is there a
> way to get Stata to take an observation from one dataset to and evaluate
> it against criteria that exists in another?
>
> Thanks for any help.
>
> -p
> ______________________________________
> Paul F. Visintainer, PhD
>
>
>
> *
> * 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/
*
* 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/
