[R] Random Effects Meta Regression

[Viechtbauer Wolfgang (STAT)]

If b is the coefficient from the meta-regression model that indicates the (average) change in the outcome measure for a one-unit increase in the corresponding explanatory variable, then 5*b is the (average) change in the outcome measure for a 5-unit increase in the explanatory variable.

Or equivalently, before fitting the model, just divide the values of that particular explanatory variable by 5. Then the coefficient from the model will give you the change in the outcome measure for a 5-unit increase.

Best,

--
Wolfgang Viechtbauer
Department of Psychiatry and Neuropsychology
School for Mental Health and Neuroscience
Maastricht University, P.O. Box 616
6200 MD Maastricht, The Netherlands
Tel: +31 (43) 368-5248
Fax: +31 (43) 368-8689
Web: http://www.wvbauer.com



----Original Message----
From: r-help-bounces at r-project.org
[mailto:r-help-bounces at r-project.org] On Behalf Of s306 Sent: Saturday,
January 15, 2011 19:27 To: r-help at r-project.org
Subject: Re: [R] Random Effects Meta Regression

> Thank you Mike - that has worked brilliantly.
>
> I have one further question that I was hoping someone on the forum
> may be able to help with.
>
> For most of my meta regressions I am interested in the impact of a
> one unit increase in the explanatory variable, however for one I want
> to estimate the effect of a 5 unit increase in my explanatory
> variable (this being the only explanatory variable in the particular
> meta regression).
>
> I haven't been able to find much documentation in the stats
> literature to guide how I may go about such a problem. Does anybody
> here have any thoughts?
>
> Many Thanks,
> Steph