Date:         Wed, 31 May 2006 13:54:03 -0400
Reply-To:     Kevin Roland Viel <kviel@EMORY.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Kevin Roland Viel <kviel@EMORY.EDU>
Subject:      Re: interaction between two continuous IV
In-Reply-To:  <20060531172049.34259.qmail@web26412.mail.ukl.yahoo.com>
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Wed, 31 May 2006, adel F. wrote:

> Dear all,
>   I would like to include an interaction term between two continuous
> independent variables IV (of different units, X1 and X2) in a multiple
> linear regression, my understanding , I can do that by  creating a new
> variable , product of the two IVs X3=X1*X2
>
>   My question, is how to interpret the parameter of X3 ? the unit of X3 is the unit of X1 and X2
>   like X1=age(yr) and X2=Weight(kg)

Could you please provide more details?  What kind of analyses are you
going to perform (proc)?  What is the outcome?  Are you going to center X1
and X2?

You could explore the impact using specific numeric examples:  Choose an
age, and compare two weights.  Choose a weight and compare two ages.

At any rate, you might want to consider using a hierarchically
well-formulated model:  keep the lower order terms and the single term
involved in any interactions, regardless of "significance".

Good luck,

Kevin

Kevin Viel
Department of Epidemiology
Rollins School of Public Health
Emory University
Atlanta, GA 30322