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

Re: st: Interaction terms in fixed effects analysis

From   Clive Nicholas <>
Subject   Re: st: Interaction terms in fixed effects analysis
Date   Sun, 8 Feb 2009 17:56:39 +0000

Tara Iyer replied to Kyle K Hood:


> 1. Why would one subtract the coefficient from the regression constant in
> analyzing the effect of expenditure in State 1 ie. 97.34217
> -0.0024748*perstudent?

Because, if you look carefully, the coefficient on -perstudent- is
negative. Kyle showed this to you without stating it in his reply.

> 2. The thing is, I am estimating a different set of dummies with xi (I had
> to
> create the variable state with State 1 = 1 and so on), and _Istate_2 and
> _Istate_3. Given this, would one still subtract the coefficient on
> perstudent
> from the constant fro State 1? Similarly for State 2?

Remember that the constant term, or intercept, shows the 'baseline'
value of the dependent variable when all independent variables are set
to 0. -state1- is dropped from your battery of state dummies because
having all of them in would fully determine the model. Since -state1-
= 0, it is thus subsumed into the intercept. However, if you wish to
keep them all, take a look at Ben Jann's user-written -devcon-
command, available from SSC:

findit devcon

or look here:

To gain a deeper understanding of how to interpret parameter estimates
in interactive regression models, you are strongly urged to read the
excellent articles by Bedeian and Mossholder (1994), Braumoller (2004)
and Brambor, Clark and Golder (2006).

Clive Nicholas

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

Bedeian A and Mossholder KW (1994) "Simple Question, Not So Simple
Answer: Interpreting Interaction Terms in Moderated Multiple
Regression", Journal of Management 20(1): 159-65.

Braumoeller BF (2004) "Hypothesis Testing and Multiplicative Interaction Terms",
International Organization 58(4): 807-20.

Brambor T, Clark WR and Golder M (2006) "Understanding Interaction
Models: Improving Empirical Analyses", Political Analysis 14(1):
*   For searches and help try:

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