Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

Re: st: test for independence for variables adding to 100%

 From federico.tedeschi@univr.it To statalist@hsphsun2.harvard.edu Subject Re: st: test for independence for variables adding to 100% Date Fri, 15 Apr 2011 10:13:46 +0200

```I think a test for independence doesn't make sense in your case: those variables are dependent by construction. However, you could evaluate how a variable affects the relative weight of the other two. To explain what I mean, being q1, q2 and q3 the rate of Elementary, Middle and High Schoolers respectively, you could see how q3 affects q1/(q1+q2).
Federico

----- Messaggio originale -----
Da: "Lim,  Raymond" <rl2240@columbia.edu>
Data: Thursday, April 14, 2011 18:11
Oggetto: st: test for independence for variables adding to 100%
A: "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>

> Hello Statalisters,
> Say you have teams composed of 3 types of people: elementary
> schoolers, middle schoolers, high schoolers. How do you test
> whether teams with a high percentage of high schooler also have
> a high percentage of elementary schoolers? The tricky part is
> the three must sum to 100% so having a high percent of one group
> automatically means having a low percent of the other groups.
>
> Thanks,
> -Raymond
>
> *
> *   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/
```