[R] Meta-regression of categorical variables

[Michael Dewey]

Dear Kammy

You might get better responses on the mailing list dedicated to 
meta-analysis in R

https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis

Note you need to register first before posting.

On 18/08/2017 10:18, Kammy Tang wrote:
> Dear metafor users,
>
>
> I am working on a meta-analysis of reliability and the correlation associations.
>
>
> I need some help about conducting categorical moderators variables.
>
>
> Questions 1: How to conduct the weighted ANOVAs assuming a mixed-effects model on the tranformed alpha coefficients/the tranformes correlation coefficients for the categorical moderator variables?
>
>
> Questions 2: How to calculate the average reliability coefficients for each category of the moderator variable?
>
>
> Take the reliablity generalization as an example. Here is an example of my code.
>
>
> #meta-analysis using transformed alpha values (using the transformation suggested by Bonett, 2002)
>
> res<-rma(measure="ABT", ai=ai, ni=size, mi=n_items, dat=data)
> res
> backtransf_res<-predict(res, transf=transf.iabt)
> backtransf_res
>
> #meta-regression of categorical variables
> #take var1 as an example of categorical moderator variable
> res_var1<-rma(measure="ABT", ai=ai, ni=size, mi=n_items, mods=~var1, dat=data)
> res_var1
> transf_res_var1<-predict(res_var1,newmods=c(1,2,3,4,5),transf=transf.iahw,digits=2)
> transf_res_var1
>
> NOTES: var1 consists of totally 5 levels/categories.
>
> Is it appropriate to conduct like that as the example code showed?
>
> Is that something wrong with the "newmods=c(1,2,3,4,5)" code?
>
>
> To be honest, this is my first time to use metafor package and use R,  I definitely wish to find out the results of the meta-analysis.
>
>
> Any help are appreciated!!
>
> Thanks a lot!
>
>
> Sincerely,
>
> Jiaxin
>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.
>
> ---
> This email has been checked for viruses by AVG.
> http://www.avg.com
>
>

-- 
Michael
http://www.dewey.myzen.co.uk/home.html