I suspect that there is, but it is non-trivial. You will need the variance
associatied with iage = 40 sex = .5 along with the covariance of those
terms with the beta-hats, plus the covariance terms from the model, just for
starters.
See Graubard, B. and Korn, E. "Predictive Margins With Survey Data",
Biometrics 55, 652-659 June 1999.
Bryan Sayer
Statistician, SSS Inc.
-----Original Message-----
From: Fred Wolfe
To: [email protected]
Sent: 7/7/03 11:04 PM
Subject: st: Confidence interval adjust differences
Is there a way to get a confidence interval in this situation?
for example
gen dummy = 1
reg depvar age sex
adjust if e(sample), by(dummy) gen(var1)
adjust iage = 40 sex = .5 if e(sample), by(dummy) gen(var2)
gen diff = var1 - var2
Is there a way to get a confidence interval for this difference? I
assume
that just ci diff is not appropriate.
Thanks,
Fred
Fred Wolfe
National Data Bank for Rheumatic Diseases
Wichita, Kansas
Tel (316) 263-2125 Fax (316) 263-0761
[email protected]
*
* 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/
