Re: [R] meta-analysis in R

From: Mike Cheung <mikewlcheung_at_gmail.com>
Date: Thu, 21 Jun 2007 22:24:34 +0800

Dear Bernd,

Please be careful in reading the example of meta-regression (12.4) in <http://cran.r-project.org/doc/vignettes/HSAUR/Ch_meta_analysis.pdf>.

In that example, the variance component was estimated under a model without any covariate. Then the estimated variance component was used as the variance component in the meta-regression with covariates. Since the variance component is based on the model without any covariate, it should be overestimated for a model with covariate. I have emailed the authors about this issue.

A better approach is to use the MiMa function provided by Wolfgang Viechtbauer.

Regards,
Mike

-- 
---------------------------------------------------------------------
 Mike W.L. Cheung               Phone: (65) 6516-3702
 Department of Psychology       Fax:   (65) 6773-1843
 National University of Singapore
 http://courses.nus.edu.sg/course/psycwlm/internet/
---------------------------------------------------------------------


On 6/21/07, Bernd Weiss <bernd.weiss_at_uni-koeln.de> wrote:

> On 21 Jun 2007 at 12:09, Irene Mantzouni wrote:
>
> Date sent: Thu, 21 Jun 2007 12:09:31 +0200
> From: "Irene Mantzouni" <ima_at_difres.dk>
> To: <r-help_at_stat.math.ethz.ch>
> Subject: [R] meta-analysis in R
>
> > I would like to combine time-series data to test for correlations
> > and
> > interactions using random and fixed effects meta-analysis.
> >
> > So, I am looking for the right packages and documentation.
> >
> > I know about meta and rmeta packages of R.
> >
> > Are there any more? What are the diffrences in brief?
>
> Yes, there are some more packages for meta-analysis.
> help.search("meta-analysis") will answer your question.
>
> Additionally, one should also mention the MiMa function, see below.
>
> Most of the packages use a method of moments estimator; MiMa offers a
> wider range of estimation methods, e.g. ML or REML (see the MiMa
> documentation for more information).
>
> > Can you please suggest some references that could be used as a guide
> > for
> > meta-analysis in R (or S-plus)?
> >
> >
>
> I know at least two references:
>
> There is a chapter on meta-analysis in Everitt, Brian, und Torsten
> Hothorn, 2006: A handbook of statistical analyses using R. Boca
> Raton: Chapman & Hall/CRC. (see also <http://cran.r-
> project.org/doc/vignettes/HSAUR/Ch_meta_analysis.pdf>)
>
> See also my reply to Lucia Costanzo and my suggestion to use the
> MiMa-package
> <http://tolstoy.newcastle.edu.au/R/e2/help/07/06/19418.html>.
>
> HTH,
>
> Bernd
>
> ______________________________________________
> R-help_at_stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
______________________________________________ R-help_at_stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Received on Thu 21 Jun 2007 - 15:07:07 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Thu 21 Jun 2007 - 15:32:08 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.