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: multiple interaction effects

From   Clive Nicholas <>
Subject   Re: st: multiple interaction effects
Date   Sat, 21 Aug 2010 01:25:48 +0100

Fabio Zona wrote:

> In my study I have three independent variables x1 x2 x3, and I have three hypotheses regarding the interactions of these variables with another fourth var z1.
> Question: do I have to test the interaction effects separately (i.e., one single model for each interaction, that is, one regression for x1z1, a different regression for x2z1...)?
> Or do I need to test these three interactions effects in one single regression (i.e., in one single regression I include: x1z1 x2z1 x3z1)? What is the difference in terms of interpretation?
> Note: the three variables x1 x2 x3  refer to constructs realted to the same phenomenon

The correct model is surely to include all the terms together by fitting

y = a + b0 + b1x1 + b2x2 + b3x3 + b4z1 + b5(x1*z1) + b6(x2*z1) + b7(x3*z1) + e

so that you obtain the best possible estimates of your interaction
terms. Fitting the models separately would mean failing to control for
your other x-covariates, which you can't possibly want, as well the
other interaction terms.

Clive Nicholas

[Please DO NOT mail me personally here, but at
<>. Please respond to contributions I make in
a list thread here. Thanks!]

"My colleagues in the social sciences talk a great deal about
methodology. I prefer to call it style." -- Freeman J. Dyson.

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index