Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

Re: st: Box-Tidwell Test

From   Maarten buis <>
Subject   Re: st: Box-Tidwell Test
Date   Tue, 26 Apr 2011 13:48:34 +0100 (BST)

--- On Tue, 26/4/11, wrote:
> But I have another questions regarding testing the linearity
> assumption.

Your explanatory variable is a dummy/indicator variable, so there
is no linearity assumption to test. Think of it this way: Say we
have age as an explanatory variable and we enter it linearly, than
we can think of that as having a group of 25 year-olds, 26 year-
olds, etc. So we compare the expected outcome of 25 year-olds with
26 year olds, 26 year olds and 27 year olds, etc. The linearity
assumption is the assumption that each of these 1 year comparisons
are equal. It is this constraint that can be tested. If we only
have two groups than there is only 1 comparison, so there is no
possibility to constrain multiple comparisons to be equal. If there
is no constraint, there is no assumption, and there is nothing to 

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index