Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: Offset variable

From   Nick Cox <>
To   "" <>
Subject   Re: st: Offset variable
Date   Mon, 9 Dec 2013 11:07:53 +0000

One of the things you learn as a journal editor is that authors very
rarely want to write the papers you want them to write. They have the
awkward habit of preferring their own ideas. I don't think anyone
wrote that paper. As the best ideas in statistics don't really go out
of date, it would be as welcome in 2013 or 2014 as in 2004.


On 9 December 2013 05:43, Richard Williams
<> wrote:
> 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:
> <>
> If somebody did successfully take Nick up on his offer I'd like to know what
> the paper was.
*   For searches and help try:

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