[R-meta] Does QE statistic in rma.mv() account for random effects as well?

[Lukasz Stasielowicz]

Dear Simon,

if you compare the output of a simple fixed effect model to a simple 
random effects model then you can see that the QE value is the same.

A reproducible example:

library(metafor)
rma(data=dat.bangertdrowns2004,yi,vi,mods=~length,method="FE")
rma(data=dat.bangertdrowns2004,yi,vi,mods=~length,method="REML")

"Test for Residual Heterogeneity:
QE(df = 44) = 96.2810, p-val < .0001"

In other words. Random effects do not influence the QE value.

You can also see it in the code that Wolfgang provides via github:
https://github.com/cran/metafor/blob/master/R/rma.mv.r (line 1500)


For some conceptual clarifications see also this paper:
Pastor, D. A., & Lazowski, R. A. (2017). On the multilevel nature of 
meta-analysis: A tutorial, comparison of software programs, and 
discussion of analytic choices. Multivariate Behavioral Research, 52(6), 
789–804. https://doi.org/10.1080/00273171.2017.1365684



Best,
Lukasz
-- 
Lukasz Stasielowicz
Osnabrück University
Institute for Psychology
Research methods, psychological assessment, and evaluation
Seminarstraße 20
49074 Osnabrück (Germany)

Am 21.01.2022 um 12:00 schrieb r-sig-meta-analysis-request using r-project.org:
> Send R-sig-meta-analysis mailing list submissions to
> 	r-sig-meta-analysis using r-project.org
> 
> To subscribe or unsubscribe via the World Wide Web, visit
> 	https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis
> or, via email, send a message with subject or body 'help' to
> 	r-sig-meta-analysis-request using r-project.org
> 
> You can reach the person managing the list at
> 	r-sig-meta-analysis-owner using r-project.org
> 
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of R-sig-meta-analysis digest..."
> 
> 
> Today's Topics:
> 
>     1. Does QE statistic in rma.mv() account for random effects as
>        well? (Simon Harmel)
> 
> ----------------------------------------------------------------------
> 
> Message: 1
> Date: Thu, 20 Jan 2022 21:01:56 -0600
> From: Simon Harmel <sim.harmel using gmail.com>
> To: R meta <r-sig-meta-analysis using r-project.org>
> Subject: [R-meta] Does QE statistic in rma.mv() account for random
> 	effects as well?
> Message-ID:
> 	<CACgv6yX9xozyJV5Nbd+dmh75UYjaGjXKwCk=Q3T_084jpNA1hg using mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
> 
> Dear Meta-Analysis Experts,
> 
> I'm running a multilevel model with metafor's rma.mv().
> 
> Does the QE statistic (Test for Residual Heterogeneity) reported by rma.mv(),
> in addition to the variance explained by moderators, also account for the
> variance components explained by random-effects (Sigmas, Taus, & Gammas)?
> 
> In other words, a significant QE in such models suggests that the true
> effects are heterogeneous beyond what has been explained by moderators AND
> random components OR just moderators?
> 
> Thank you,
> Simon
> 
> 	[[alternative HTML version deleted]]
> 
> 
> 
> 
> ------------------------------
> 
> Subject: Digest Footer
> 
> _______________________________________________
> R-sig-meta-analysis mailing list
> R-sig-meta-analysis using r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis
> 
> 
> ------------------------------
> 
> End of R-sig-meta-analysis Digest, Vol 56, Issue 18
> ***************************************************