[R-meta] FE Model

Viechtbauer, Wolfgang (SP) wolfg@ng@viechtb@uer @ending from m@@@trichtuniver@ity@nl
Sun Dec 23 20:49:54 CET 2018


This is not a reproducible example. For details on how to create reproducible examples, please see:

- https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example
- http://adv-r.had.co.nz/Reproducibility.html
- https://cran.r-project.org/web/packages/reprex/vignettes/reprex-dos-and-donts.html

Best,
Wolfgang

-----Original Message-----
From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On Behalf Of Julie Webbs
Sent: Sunday, 23 December, 2018 20:19
To: r-sig-meta-analysis using r-project.org
Subject: Re: [R-meta] FE Model

On Sun, Dec 23, 2018 at 7:10 PM Viechtbauer, Wolfgang (SP) <
wolfgang.viechtbauer using maastrichtuniversity.nl> wrote:

> Please reply to the mailing list, not just to me. Also, please provide a
> fully reproducible example.
>
> Best,
> Wolfgang
>
> -----Original Message-----
> From: Julie Webbs [mailto:webbsjulie using gmail.com]
> Sent: Sunday, 23 December, 2018 19:31
> To: Viechtbauer, Wolfgang (SP)
> Subject: Re: [R-meta] FE Model
>
> Thank you, Wolfgang
>
> Here is the data. If you use the method= "FE",  the label  will read  the
> "RE Model" , not the  "FE Model" in the forest plot. tau^2= 0. Thank you
> for your help.
>
> Study   Ne      Me      Se      Nc      Mc      Sc
> Study 1 80      71      12      80      69      8
> Study 2 69      83      11      69      80      9
> Study 3 92      87      10      92      85      8
>
> On Sun, Dec 23, 2018 at 5:43 PM Viechtbauer, Wolfgang (SP) <
> wolfgang.viechtbauer using maastrichtuniversity.nl> wrote:
> Hi Julie,
>
> Could you provide a reproducible example illustrating the issue?
>
> This works just fine:
>
> yi <- c(.1, .2, .3)
> vi <- rep(.01, 3)
> res <- rma(yi, vi, method="FE")
> forest(res)
>
> Maybe tau^2 is estimated to be zero in your case? Then the plot will look
> the same, except for the labeling:
>
> res <- rma(yi, vi)
> res
> forest(res)
>
> Best,
> Wolfgang
>
> -----Original Message-----
> From: R-sig-meta-analysis [mailto:
> r-sig-meta-analysis-bounces using r-project.org] On Behalf Of Julie Webbs
> Sent: Sunday, 23 December, 2018 18:23
> To: r-sig-meta-analysis using r-project.org
> Subject: Re: [R-meta] FE Model
>
> Sorry i meant I get the RE Model
>
> On Sun, Dec 23, 2018 at 5:18 PM Julie Webbs <webbsjulie using gmail.com> wrote:
>
> > Hi
> > I have set method = "FE" in rma(), but in the forest plot , I get the RM
> > Model, and the results do not change when I use method = "FE" in metafor.
> > Is it a bug or I missed something?
> > Any help?
> > Julie



More information about the R-sig-meta-analysis mailing list