Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Richard Williams <richardwilliams.ndu@gmail.com> |
To | statalist@hsphsun2.harvard.edu, "<statalist@hsphsun2.harvard.edu>" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: Offset variable |
Date | Mon, 09 Dec 2013 00:43:04 -0500 |
At 10:53 PM 12/8/2013, Stephen A. Crowder wrote:
I am developing an ordinal logistic regression model examining a factor with several levels on my dependent variable. That part is straight forward enough but I have a main independent variable that ide like to control for in the examination of all of the other independent variables. My question is would I need to make this an "offset variable" in my models? I've been looking through the literature and there's no clear answer available.Sent from my iPhone
First off, if you have a new topic you should start a new thread rather than reply to an old post. Even if you change the topic the threading gets thrown off in the archives. Also the totally unrelated extraneous text from the old thread that you quoted is distracting.
I think you probably just want to include the variable as another independent variable. In Poisson and related models offset is sometimes used as an alternative to the exposure option, e.g. it provides a way of dealing with cases that have been at risk for differing amounts of time. I don't think I have ever seen an example that used offset in an ologit model. I'd be curious to know if there are situations in which it makes sense.
I don't know if the offer is still good, but 9 years ago Nick Cox said SJ would be interested in a paper that discussed the practical uses of offset with commands like ologit:
<http://www.stata.com/statalist/archive/2004-10/msg00002.html>http://www.stata.com/statalist/archive/2004-10/msg00002.htmlIf somebody did successfully take Nick up on his offer I'd like to know what the paper was.
------------------------------------------- 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 WWW: http://www.nd.edu/~rwilliam * * 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/