Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: areg versus xtreg
From
"Gupta, Sumedha" <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: areg versus xtreg
Date
Tue, 15 Mar 2011 16:53:03 +0000
Hi,
Using survey data I want to estimate sibling fixed effects model. The data provides me with p weights. I run the following two models:
xi: areg eduyearsW4 agesi if pophsib1==1 [pweight=gswgt4_2], absorb (famid) vce(cluster famid)
xtreg eduyearsW4 agesi if pophsib1==1 [pweight=gswgt4_2], i(famid) fe vce(cluster famid)
Firstly, I am not sure which is the correct model. In theory shouldn't these two models give exactly the same point estimates and standard errors? Secondly, I am not being able to run the weighted xtreg because for some reason stata gives me an error for the xtreg stating "weight must be constant within famid". The weights should be constant within famid ... so I don't know how they end up being different but I don't know how to check that.
If I run the xtreg non-weighted I get completely different results from the areg. Can somebody please help me resolve this mystery.
I will really appreciate your input.
Sincerely,
Sumedha.
*
* 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/