Date: Fri, 2 Jan 2009 17:40:16 -0500
Reply-To: Kevin Viel <citam.sasl@GMAIL.COM>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: Kevin Viel <citam.sasl@GMAIL.COM>
Subject: Re: stats jargon - "controlling for the effects of"
On Thu, 1 Jan 2009 14:24:41 -0800, paul wilson <paulwilsn@YAHOO.COM> wrote:
>so what you're saying is that "controlling for the effects of AGE"
means "considering the effects of AGE"?
>Did I get it right?
Context becomes important to the answers of this question. If you are
mathematical, then simply looking at the expressions should clarify it. In
short, when one controls for the effects of age or another covariate, then
we hold age constant. Plots can be helpful, especially in the case of an
interaction between age and the variable of interest. Curves for each age
of interest can be overlayed.