[R-meta] Forest code error in multivariate analysis Metafor

[Ayesha Sadozai]

Dear Reza
You are a life-saver! Thank you. I do not know how to change my settings to plan text, can you suggest how I do this?

Also, make sure you make the best use of the `random =` argument. Currently, it does seem that `random = ~ 1 |`Study No.` is ignoring the fact that some studies may contribute more than one effect size estimate in your dataset. If each study actually contributes only one effect size, then, essentially you don't need to use rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>(). Rather, you can use rma(). Please check out the archives (https://stat.ethz.ch/pipermail/r-sig-meta-analysis/<https://protect-au.mimecast.com/s/GPWUC71R2NTAXMk4VHRypuG?domain=stat.ethz.ch>) to learn more about rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>().

Re your above point, I thought because I am doing a multilevel analysis I need the .mv to indicate this, and yes each study no. (within this it has unit of EF measure) contributes a unique effect size.

Thanks again 😊
Ayesha

From: Reza Norouzian <rnorouzian using gmail.com>
Sent: Friday, 15 October 2021 2:14 PM
To: Ayesha Sadozai <asad6836 using uni.sydney.edu.au>
Cc: r-sig-meta-analysis using r-project.org
Subject: Re: [R-meta] Forest code error in multivariate analysis Metafor

Dear Ayesha,

It would be very helpful if you could consider using plain text to post your queries on the list.

Assuming your model syntax is correct and runs fine on your end, does the following run on your machine?

metafor::forest(res)

If yes, then it might be a simple conflict with another package that uses a function with the same name.

Kind regards,
Reza

ps. Also, make sure you make the best use of the `random =` argument. Currently, it does seem that `random = ~ 1 |`Study No.` is ignoring the fact that some studies may contribute more than one effect size estimate in your dataset. If each study actually contributes only one effect size, then, essentially you don't need to use rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>(). Rather, you can use rma(). Please check out the archives (https://stat.ethz.ch/pipermail/r-sig-meta-analysis/<https://protect-au.mimecast.com/s/GPWUC71R2NTAXMk4VHRypuG?domain=stat.ethz.ch>) to learn more about rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>().

On Thu, Oct 14, 2021 at 9:11 PM Ayesha Sadozai <asad6836 using uni.sydney.edu.au<mailto:asad6836 using uni.sydney.edu.au>> wrote:
Dear All and Wolfgang,

My research looks at seven paediatric executive function domains (working memory, response inhibition, attention, set switching, set shifting, fluency and planning) across a range of neurodevelopmental disorders in 78 studies. These disorders include ADHD, Autism, Tourettes, FASD and Learning disorders. My data looks at executive function (EF) measures that load on the 7 areas. I have established that the codes needed are come under the rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv> analysis and have started to run a few analyses.

I am running  codes on my sample that has a 2 multilevel structure, see codes below (1st is initial analysis and second is including a moderator analysis)
1. res.ml<https://protect-au.mimecast.com/s/QbkaC81V0PT653RDPHzuxp6?domain=res.ml> <- rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>(yi, vi, random = ~ 1 |`Study No.`, data=ASDvsADHD_Control_Clean,slab=paste(ASDvsADHD_Control_Clean$`Study_Year`,sep=""))
print(res.ml<https://protect-au.mimecast.com/s/QbkaC81V0PT653RDPHzuxp6?domain=res.ml>, digits=3)
forest(res.ml<https://protect-au.mimecast.com/s/QbkaC81V0PT653RDPHzuxp6?domain=res.ml>)

2. res <- rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>(yi, vi, random = ~ 1 |`Study No.`, mods=`EF_Domain_No`, data=ASDvsADHD_Control_Clean, slab=paste(ASDvsADHD_Control_Clean$`Study_Year`,sep=""))
print(res, digits=3)
forest(res)

When I run this I get this error, Error in UseMethod("forest") :
  no applicable method for 'forest' applied to an object of class "c('rma.mv<https://protect-au.mimecast.com/s/diWfC6XQ4Lfr6kKj0Sxspj2?domain=rma.mv>', 'rma')"

I am not sure what I am doing wrong here and I have tried to read to manual to see where my error could be, any assistance is appreciated 😊

Kind Regards,
Ayesha Sadozai | PhD Candidate
Autism Clinic for Translational Research, Brain and Mind Centre
THE UNIVERSITY OF SYDNEY
94 Mallett St<https://protect-au.mimecast.com/s/n7WuC0YKPvipGkj0SwhSEc?domain=google.com<https://protect-au.mimecast.com/s/3NzYC3QNPBipg3Q69fqzy6O?domain=google.com>> | The University of Sydney | NSW | 2006
E asad6836 using uni.sydney.edu.au<mailto:asad6836 using uni.sydney.edu.au><mailto:marilena.demayo using sydney.edu.au<mailto:marilena.demayo using sydney.edu.au>>  | W sydney.edu.au<https://protect-au.mimecast.com/s/Xw2EC91WPRTkWnBLNHZ3lPC?domain=sydney.edu.au><https://protect-au.mimecast.com/s/8qnyCgZ0N1iDAq85toeIeb?domain=sydney.edu.au/<https://protect-au.mimecast.com/s/Qql7C4QOPEiB2P1M9CB2ekp?domain=sydney.edu.au/>>   | P 02) 9351 0507 | Wed-Fri only


        [[alternative HTML version deleted]]

_______________________________________________
R-sig-meta-analysis mailing list
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://protect-au.mimecast.com/s/n0PNC5QPXJiZP8G5ps2ZlhM?domain=stat.ethz.ch>

	[[alternative HTML version deleted]]