Be aware , -svy: tab- and -svy; prop- have different formulas for
confidence intervals. -svy: tab- does the CIs on the logit scale,
then back transforms. This will make a difference if your
probabilities are close to zero or one.
-Steve
> -----Ursprungligt meddelande-----
> Från: [email protected]
> [mailto:[email protected]] För Martin Weiss
> Skickat: den 18 december 2009 15:56
> Till: [email protected]
> Ämne: st: AW: svy tab and lincom
>
>
> <>
>
> Just use -proportion- itself, then:
>
>
> *************
> webuse nhanes2b, clear
> svyset psuid [pweight=finalwgt], strata(stratid)
> svy: prop race
> te _b[White]=_b[Black]
> *************
>
>
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected]
> [mailto:[email protected]] Im Auftrag von Tomas Lind
> Gesendet: Freitag, 18. Dezember 2009 15:52
> An: [email protected]
> Betreff: st: svy tab and lincom
>
> Statalisters!
>
>
> I have survey data and want to compare proportion "yeas" between areas. Is
> it possible to do that with lincom after estimation with tab?
>
> svy , subpop(ar==1) : tab area disturbed , row ci
>
> lincom [area]St - [area]Up // Do not work
>
>
> /Tomas
>
> *
> * 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/
>
>
> *
> * 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/
>
--
Steven Samuels
[email protected]
18 Cantine's Island
Saugerties NY 12477
USA
845-246-0774
*
* 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/
