Hm, just noticed that as well ... guess this has not solved the problem
quite yet ...
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Richard Williams
Sent: Tuesday, February 19, 2008 3:13 PM
To: [email protected]; [email protected]
Subject: RE: st: Multiple mean comparisons with complex survey design -
Richard
At 03:11 PM 2/19/2008, Sven Klingemann wrote:
>Thanks Richard. I guess I got confused by the Stata Manual:
You can also set it up as a regression problem, in which case you
could do it in Stata 9:
webuse nhanes2f
xi: svy: reg health i.race
test _Irace_2 _Irace_3, mtest(b)
As I think about it though, I am not sure if this is giving you
exactly what you want. It is giving you comparison of 1 versus 2 and
1 versus 3, but not 2 versus 3. If you were using the oneway command
with non-svy data, you would get all three contrasts. So, maybe this
doesn't solve your problem after all?
Of course, doing a bonferroni adjust by hand isn't all that hard and
could perhaps be automated. Maybe set up a loop to do a bunch of
test commands.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/
