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]

Re: st: Testing the extent of difference between two coefficients in the same model


From   Richard Williams <[email protected]>
To   [email protected], [email protected]
Subject   Re: st: Testing the extent of difference between two coefficients in the same model
Date   Tue, 31 Jan 2012 11:19:22 -0500

At 06:34 AM 1/31/2012, Maarten Buis wrote:
On Mon, Jan 30, 2012 at 11:12 PM, David Hoaglin wrote:
>  A model in
> which the two coefficients are equal is the same as the model in which
> the predictor associated with that coefficient is the sum of "old" and
> "new."

This is a trick that is often forgotten (at least in my discipline),
but can have surprisingly useful applications beyond adding linear
constraints to models that do not allow the -constraint- option. I
submitted a Stata tip on this topic a couple of days ago.
<http://www.maartenbuis.nl/wp/sumconstr.html>

-- Maarten

As Maarten's tip shows, this approach lets you do likelihood ratio tests of the constraint, whereas the -test- command does a Wald test. Starting with Stata 11, the -logit- and -ologit- commands allowed the use of the -constraint- option, so the tip isn't quite as necessary as it used to be, although I think it may be just as easy if not easier to compute the sum as it is to specify the constraints. For teaching purposes I like to write out the equations and illustrate approaches like this just so my students understand the constraints being imposed and why this works.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  [email protected]
WWW:    http://www.nd.edu/~rwilliam

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


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