Subgroup analysis after Meta analysis

General help and assistance with jamovi. Bug reports can be made at our issues page: https://github.com/jamovi/jamovi/issues . (If you're unsure feel free to discuss it here)
Post Reply
BeginnerA
Posts: 15
Joined: Wed Aug 17, 2022 7:40 pm

Subgroup analysis after Meta analysis

Post by BeginnerA »

Hello everyone
Just downloaded Jamovi days ago and I want to thank all who made this software possible.

I have a question about Subgroup analysis after getting the original forest plot of meta-analysis; can we do it in Jamovi? and How (if possible)?

Thanks a lot!
apavlo
Posts: 9
Joined: Thu Aug 18, 2022 2:00 pm

Re: Subgroup analysis after Meta analysis

Post by apavlo »

My understanding is that you can't do this with the MAJOR package yet and it is so sad... It also really sucks that you can't unlog the forest plots. It also sucks that online for metafor R there is only an RR or OR example to copy Cochrane's vastly superior forest plot design and not for mean differences.

https://www.metafor-project.org/doku.ph ... lot_revman
apavlo
Posts: 9
Joined: Thu Aug 18, 2022 2:00 pm

Re: Subgroup analysis after Meta analysis

Post by apavlo »

So yeah you are kinda screwed there as am I. The only option is to use Cochrane's RevMan, however you are locked to use Dersimonian-Laird estimator (DL) which, as opposed to Restricted ML (REML) is proven to suck with high heterogeneity data and will mistakenly produce significant results when there shouldn't be.

So here we are in 2022 and there is still no easy to use an adequate open-source solution for meta-analysis.
BeginnerA
Posts: 15
Joined: Wed Aug 17, 2022 7:40 pm

Re: Subgroup analysis after Meta analysis

Post by BeginnerA »

Thank you for your feedback..really appreciated.
BeginnerA
Posts: 15
Joined: Wed Aug 17, 2022 7:40 pm

Re: Subgroup analysis after Meta analysis

Post by BeginnerA »

Just found this about JASP here:https://github.com/jasp-stats/jasp-issues/issues/373, I am not 100% sure if this applies to Jamovi too, but I think will apply.

"Sub-analyses are possible with the case filter feature, and running a meta-analysis on subsets of cases. But combining them in forest plots as in the example is not implemented. If I remember correctly I decided to not add that mainly because it would require an additional user interface, and you can simply do it with sub-grouping your data and running a meta analysis."
User avatar
jonathon
Posts: 2613
Joined: Fri Jan 27, 2017 10:04 am

Re: Subgroup analysis after Meta analysis

Post by jonathon »

yes, if all you're trying to do is analyse a subset of your data, you can just use filters.

jonathon
Mira23
Posts: 1
Joined: Wed Aug 31, 2022 2:53 am
Location: United States
Contact:

Re: Subgroup analysis after Meta analysis

Post by Mira23 »

apavlo wrote:My understanding is that you can't do this with the MAJOR package yet and it is so sad... It also really sucks that you can't unlog the forest plots. It also sucks that online for metafor R there is only an RR or OR example to copy Cochrane's vastly superior forest plot design and not for mean differences.

https://www.metafor-project.org/doku.ph ... lot_revman
I've also been using Jamovi for a while, and this hasn't been possible. Is the above link your project?
Post Reply