# st: RE: Interaction term for dummy variables

 From "Moore, Jeffrey E" To Subject st: RE: Interaction term for dummy variables Date Thu, 24 Feb 2005 15:15:02 -0500

```You are doing this correct.  Note that the only '1' for male*backpain is
when you actually have a male with back pain.  Thus, the coefficient
associated with this value of 1 will represents a unique effect of back
pain on males that isn't there on females.  And there's your
interaction.

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of anju parthan
Sent: Thursday, February 24, 2005 2:49 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: Interaction term for dummy variables

Hi All

I am running a negative binomial regression.  Majority
of the independent variables are categorical for
example gender, ethnicity, occupation, backpain
(presence=1 and absence of back pain=0) etc. So I have
dummy coded these categorical variables. For example,
gender was dummy coded as Male. I also want to create
an interaction term between some of these dummy coded
variables. For example, gender and back pain.

Here's how I calculated the interaction term
Male*BackPain= Male x BackPain

ID      Male   BackPain  Male*BackPain

1       1       0         0 (male without back pain)
2       1       0         0 (male without back pain)
3       0       1         0 (female with back pain)
4       0       0         0 female without backpain)
5       1       1         1 (male with back pain)
6       1       1         1 (male with back pain)
7       1       0         0 (male without back pain)
8       0       0         0 (female without backpain)
9       1       0         0 (male without back pain)
10      0       1         0 (female with back pain)

And I think the xi command i.e
xi i.gender*i.backpain

gives the same result.

However, I am concerned that if we calculate the
interaction terms by multiplying the two dummy coded
variables, in this case Male and BackPain,  we are
combining some of the categories into the same group.

For example,in the above sample

ID=1 &  Male*BackPain=0 represents male without back
pain, whereas
ID=3 &  Male*BackPain=0 represents female with back
pain, and
ID=8 &  Male*BackPain=0 represents female without back
pain.

Is that right or am I missing something trivial here?

I would really appreciate if someone can throw some
light on how to calculate the interaction terms
between dummy coded categorical variables.

Regards
Anju

=====
____________________________________________________________

Anju Parthan,
Doctoral Candidate,
The University of Texas at Austin, PHAR-PHARMACY ADMIN
1 UNIVERSITY STATION A 1930, AUSTIN, TX-78712
Tel: (512) 459-4942; Fax: (512) 471-8762

__________________________________
Do you Yahoo!?
Yahoo! Mail - Helps protect you from nasty viruses.
http://promotions.yahoo.com/new_mail
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```