[R-meta] Compiling different design in the same met-analysis
Dr. Gerta Rücker
ruecker @end|ng |rom |mb|@un|-|re|burg@de
Mon May 3 20:09:25 CEST 2021
Hi Gladys,
You may pool all effects in a meta-analysis, using "design" as a
moderator. In meta-analysis, this is called a subgroup analysis (for
example by Cochrane). You then get both within-subgroup effects and a
pooled effect, and also a test of treatment--design interaction, that
says whether the treatment effect is different between designs. Thus you
have all what you are interested in. However, in your interpretation you
have to account for the different character of the studies: In a
two-group parallel design, if it is randomized (you did not mention
whether it is), you can expect an unbiased estimate of the treatment
effect. In a pre-post design, you must expect all kinds of biases (to
mention only regression to the mean) and also, as Michael said,
different variation. Therefore you have to interpret results with caution.
Best, Gerta
Am 03.05.2021 um 19:42 schrieb Gladys Barragan-Jason:
> Hi Gerta and Michael,
> I am not sure to understand. I am not saying the the effect size are
> different. They are comparable but of course differ in term of ci
> since the number of studies, participants are different. I would like
> to know whether we can make obtain an overall effect size while
> controlling for design. So maybe the answer is no.
> Thanks
> Gladys
>
> Le lun. 3 mai 2021 à 19:11, Dr. Gerta Rücker
> <ruecker using imbi.uni-freiburg.de <mailto:ruecker using imbi.uni-freiburg.de>> a
> écrit :
>
> Technically, you may conduct a meta-analysis of these two effects and
> obtain something between. The question is how to interpret this.
>
> Best,
>
> Gerta
>
> Am 03.05.2021 um 19:06 schrieb Michael Dewey:
> > Yes, exactly. After all if you show two things are different you
> > cannot say they are the same.
> >
> > Michael
> >
> > On 03/05/2021 15:59, Gladys Barragan-Jason wrote:
> >> Okay, so you can't obtain an overall effect size while controlling
> >> for design?
> >>
> >> Le lun. 3 mai 2021 à 14:36, Michael Dewey
> <lists using dewey.myzen.co.uk <mailto:lists using dewey.myzen.co.uk>
> >> <mailto:lists using dewey.myzen.co.uk
> <mailto:lists using dewey.myzen.co.uk>>> a écrit :
> >>
> >> If you include a moderator you do not get an overall effect
> >> because by
> >> including it you are effectively saying there is no single
> overall
> >> effect.
> >>
> >> On 03/05/2021 12:24, Gladys Barragan-Jason wrote:
> >> > Hi Michael,
> >> > Thanks a lot for your quick response. Here are answers
> and other
> >> > questions below.
> >> >
> >> > Le lun. 3 mai 2021 à 12:41, Michael Dewey
> >> <lists using dewey.myzen.co.uk <mailto:lists using dewey.myzen.co.uk>
> <mailto:lists using dewey.myzen.co.uk <mailto:lists using dewey.myzen.co.uk>>
> >> > <mailto:lists using dewey.myzen.co.uk
> <mailto:lists using dewey.myzen.co.uk>
> >> <mailto:lists using dewey.myzen.co.uk
> <mailto:lists using dewey.myzen.co.uk>>>> a écrit :
> >> >
> >> > Dear Gladys
> >> >
> >> > Comments in-line
> >> >
> >> > On 03/05/2021 08:13, Gladys Barragan-Jason wrote:
> >> > > Dear all,
> >> > >
> >> > > I am doing a meta-analysis on experimental data
> on the
> >> impact on
> >> > > several behavioral interventions including both
> *pre-post
> >> studies*
> >> > > (measurement of a trait before and after the
> intervention)
> >> *and
> >> > control
> >> > > vs. treatment studies *(measurement after a control
> >> intervention vs.
> >> > > measurement after the intervention).
> >> >
> >> > So the first design just has one group which is measured
> >> twice and the
> >> > second design has two parallel groups which are each
> measured
> >> once?
> >> >
> >> >
> >> > Exactly!
> >> >
> >> >
> >> > > I am interested in the effect size of each type of
> >> intervention on a
> >> > > specific trait that is common to all studies.
> >> > >
> >> > > I would like to know whether it is correct to
> compile all
> >> studies
> >> > from
> >> > > one type of intervention (whatever the type of
> >> comparisons:
> >> > pre-pot and
> >> > > control vs. treatment group together) with pre- and
> >> control being as
> >> > > control and post and treatment being as treatment.
> >> > >
> >> >
> >> > I do not think that is going to work well. Although
> the two
> >> designs
> >> > could be considered as estimating the same effect their
> >> variability
> >> > should be very different since in design 1 you have
> reduced
> >> the effect
> >> > of individual variability. If you do include both
> designs
> >> in one
> >> > analysis I would have thought it mandatory to include a
> >> moderator with
> >> > two levels for design.
> >> >
> >> > This makes sense. When I do this, I then obtain two
> effect sizes
> >> (one
> >> > for each design); (in having mods=~design-1). Do you
> know how I
> >> can get
> >> > the overall effect size?
> >> >
> >> >
> >> > > I have a second question about how to thank the
> >> > > r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>
> >> <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>>
> >> > <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>
> >> <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>>>
> >> > > <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>
> >> <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>>
> >> > <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>
> >> <mailto:r-sig-meta-analysis using r-project.org
> <mailto:r-sig-meta-analysis using r-project.org>>>> list for all their help
> >> > > (acknowledgements in a paper).
> >> >
> >> > I would have thought the URL
> >> > https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis//
> >> <https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis//>
> >> >
> <https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis//
> >> <https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis//>>
> >> > was better. How to do this will also depend on
> custom and
> >> practice in
> >> > your scientific discipline, some journals in mine
> require
> >> people who
> >> > are
> >> > acknowledged to give their consent.
> >> >
> >> >
> >> > Ok! Thanks a lot!
> >> >
> >> > Best,
> >> > Gladys
> >> >
> >> >
> >> > Michael
> >> >
> >> > >
> >> > > Thanks a lot for your help!
> >> > >
> >> > > Have a great day,
> >> > >
> >> > > Gladys
> >> > >
> >> > > --
> >> > >
> >> > > ------------------------------------------
> >> > >
> >> > > Gladys Barragan-Jason, PhD. ____ Website
> >> > >
> <https://sites.google.com/view/gladysbarraganjason/home
> >> <https://sites.google.com/view/gladysbarraganjason/home>
> >> > <https://sites.google.com/view/gladysbarraganjason/home
> >> <https://sites.google.com/view/gladysbarraganjason/home>>>
> >> > >
> >> > > Station d'Ecologie Théorique et Expérimentale
> (SETE)____
> >> > >
> >> > > CNRS de Moulis____
> >> > >
> >> > > image.pngimage.png____
> >> > >
> >> > >
> >> > >
> >> > >
> >> > >
> >> >
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient
>
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient>
>
> >>
> >> >
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient
>
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient>>>
>
> >>
> >> >
> >> > > Virus-free. www.avg.com
> <http://www.avg.com> <http://www.avg.com>
> >> <http://www.avg.com <http://www.avg.com>>
> >> > >
> >> >
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient
>
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient>
>
> >>
> >> >
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient
>
> >>
> <http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient>>>
>
> >>
> >> >
> >> > >
> >> > >
> >> > > <#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>
> >> > >
> >> > > _______________________________________________
> >> > > R-sig-meta-analysis mailing list
> >> > > R-sig-meta-analysis using r-project.org
> <mailto:R-sig-meta-analysis using r-project.org>
> >> <mailto:R-sig-meta-analysis using r-project.org
> <mailto:R-sig-meta-analysis using r-project.org>>
> >> > <mailto:R-sig-meta-analysis using r-project.org
> <mailto:R-sig-meta-analysis using r-project.org>
> >> <mailto:R-sig-meta-analysis using r-project.org
> <mailto:R-sig-meta-analysis using r-project.org>>>
> >> > >
> https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis
> >> <https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis>
> >> > <https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis
> >> <https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis>>
> >> > >
> >> >
> >> > --
> >> > Michael
> >> > http://www.dewey.myzen.co.uk/home.html
> >> <http://www.dewey.myzen.co.uk/home.html>
> >> > <http://www.dewey.myzen.co.uk/home.html
> >> <http://www.dewey.myzen.co.uk/home.html>>
> >> >
> >> >
> >> >
> >> > --
> >> >
> >> > ------------------------------------------
> >> >
> >> > Gladys Barragan-Jason, PhD. ____ Website
> >> > <https://sites.google.com/view/gladysbarraganjason/home
> >> <https://sites.google.com/view/gladysbarraganjason/home>>
> >> >
> >> > Station d'Ecologie Théorique et Expérimentale (SETE)____
> >> >
> >> > CNRS de Moulis____
> >> >
> >> > image.pngimage.png____
> >> >
> >> >
> >> >
> >>
> >> -- Michael
> >> http://www.dewey.myzen.co.uk/home.html
> >> <http://www.dewey.myzen.co.uk/home.html>
> >>
> >
>
[[alternative HTML version deleted]]
More information about the R-sig-meta-analysis
mailing list