Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: doing a t test after svrmean

From   Nick Winter <>
Subject   Re: st: doing a t test after svrmean
Date   Mon, 15 Mar 2004 14:19:29 -0500

At 11:20 AM 3/15/2004 -0600, you wrote:


I am using the SVR commands because I am using replicate weights.
If I want to do a ttest after svrmean, how do i get an accurate result since
stnadard errors are different?


Namratha Kandula
The "SVR" commands are a set of commands I wrote to deal with estimation in complex samples using replication methods. They are in many respects analogous to Stata's "SVY" commands, which handle complex samples using Taylor Series linearization.

Whichever approach you are using, to do a t-test, you use the -test- command after svrmean (or svymean), rather than the -ttest- command.


. svrmean x
. test x=2

. svrmean x y
. test x=y

And so on.

SEe the "test for svy" section of the SVY reference manual for more details. (And note that you should be able to do everything there after the SVR commands, as well.)

--Nick Winter

Namratha Kandula, MD, MPH
University of Chicago
MC 2007
5841 S. Maryland Avenue
Chicago, IL 60622
phone: 773-834-9180
fax: 773-702-1295

*   For searches and help try:
Nicholas Winter 607.255.8819 t
Assistant Professor 607.255.4530 f
Department of Government e
308 White Hall w
Cornell University
Ithaca, NY 14853-4601
* For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index