[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: AW: st: Logistic Regression_Unequal Ns (outcomes)

From   Richard Williams <>
To   "" <>, "" <>
Subject   Re: AW: st: Logistic Regression_Unequal Ns (outcomes)
Date   Sun, 08 Mar 2009 12:00:32 -0500

At 10:30 AM 3/8/2009, Chao Yawo wrote:
Thanks Martin and Richard,

I am thinking of using the relogit command, but I am wondering how i
could do so, while incorporating complex sampling design

Should I just svyset my data and then run the relogit OR

should I just use the relogit command, but specify the weight option
on the command. Even if I do this, there is no way to specify the
strata or the sampling unit commands directly, so would my model be
estimated correctly?

thanks for all your help.

rgds, CY

It isn't hard to add svy support to a program. For example, my oglm program includes the following line:

program oglm, eclass byable(recall) sortpreserve properties(swml svyr svyb svyj or irr rrr hr eform)

I believe the program also has to allow iweights. See -help program- and -help program_properties-. Whether there is some reason this would be an awful idea with -relogit- or impossible to do, I don't know. If you are going to try to do your own programming, you may also wish to take a look at (see especially chapter 11 on survey data anlysis)

Whenever you do alter someone else's program, it is a good idea to rename it so the original and revised program do not get confused.

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu

*   For searches and help try:

© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index