Bookmark and Share

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: Confidence intervals after -xtmixed-


From   "P. Praeg" <[email protected]>
To   [email protected]
Subject   st: Confidence intervals after -xtmixed-
Date   Mon, 24 Mar 2014 19:01:23 +0100

Dear all:

I am interested in obtaining confidence intervals for the sum of the empirical Bayes residuals plus the overall regression coefficient after fitting a random effects model.

Specifically, I'm fitting a model similar to this one:

use http://www.stata-press.com/data/r12/pig, clear

xtmixed weight week || id: week, var cov(uns)

I am predominately interested in the slope variation of "week." So doing this:

predict BLUP*, reffects
predict BLUPse*, reses

gives me the id-specific residuals and their standard errors
for the intercept and the slope of "week."

This way, I can e.g. obtain a "caterpillar plot" for the id-specific slope residuals of "week":

serrbar BLUP1 BLUPse1 id, yline(0) scale(1.96)

This is close to what I want, but not exactly.

What I want is a plot like this:

gen weekeffect = _b[week] + BLUP1
graph dot weekeffect, over(id) vertical

but then with confidence intervals.

My question now is: Is there a straight forward (and correct) way in Stata to obtain a standard error for the sum of _b[week] and BLUP1?

Thank you for your consideration!
Patrick


--
Patrick Präg
ICS/Department of Sociology
Faculty of Social and Behavioral Sciences
University of Groningen
Grote Rozenstraat 31
9712 TG Groningen, The Netherlands

Tel: +31 (0)50 363 7620
Email: [email protected]

http://www.rug.nl/staff/p.praeg
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index