[Rmeta] Comparing several predictors and responses & most appropriate model
Alicia Foxx
@oxx @endng rom u@northwe@tern@edu
Tue Dec 27 17:34:57 CET 2022
Hello Everyone,
My coauthor and I are working on a metaanalysis in which we want to know
the relationship (direction and magnitude) between a variable (mean
difference on the xaxis) and a log response ratio (on the yaxis). As a
toy example, we want to know if differences in beak length between bird
species predict fitness outcomes across studies. From each study, we
collected differences in beak length between species as well as fitness
outcomes of birds alone (i.e., not in competition) and in competition.

Difference (raw mean difference) in beak length:

A beak length  B beak length

A beak length  C beak length

B beak length  A beak length

C beak length  A beak length

Fitness outcomes (log response ratio):

log(mean(A fitness with B)/mean(fitness alone))

log(mean(A fitness with C)/mean(fitness alone))

log(mean(B fitness with A)/mean(fitness alone))

log(mean(C fitness with A)/mean(fitness alone))

We want to use such comparisons from *many studies* to obtain a general
relationship between differences in beak length and fitness outcomes.

Fitness outcomes:

log(mean(A fitness with B)/mean(fitness alone)) ~ AB (beak length)

log(mean(A fitness with C)/mean(fitness alone)) ~ AC (beak length)

log(mean(B fitness with A)/mean(fitness alone)) ~ BA (beak length)

log(mean(C fitness with A)/mean(fitness alone)) ~ CA (beak length)

As you can see, each study contributes several log response ratios
(i.e., y effect sizes) and several raw mean differences (i.e., predictor
effect sizes). We have several questions:

What is the best model to assess an overall relationship between
differences in beak length and fitness across studies?

It seems that a metaregression would work for this question but
our concern is that this is an inappropriate model given that we’re
comparing one effect size (mean difference) with another (log response
ratio). We investigated bivariate metaanalyses, but the
inputs appear to
both be outcomes.

How do we account for nonindependence at the level of comparison
(Species A vs. Species B, and species B vs. species A), and
study. We’ve
thought about nested random effects or even mathematical
corrections for
the nonindependence.

We’d greatly appreciate any advice that can be shared.
Thank you,
Alicia
________________________________________
*Dr. Alicia Foxx, MS, PhD*
she/her/hers
Research Scientist
The Chicago Botanic Garden & New Roots for Restoration
<http://www.newrootsforrestoration.org/>
Adjunct Professor: Northwestern University
Associate Editor: Ecological Solutions and Evidence
<https://besjournals.onlinelibrary.wiley.com/journal/26888319>
ResearchGate <https://www.researchgate.net/profile/AliciaFoxx> & Google
Scholar <https://scholar.google.com/citations?user=nlWrL0YAAAAJ&hl=en>
E: afoxx using chicagobotanic.org
_________________________________________
[[alternative HTML version deleted]]
More information about the Rsigmetaanalysis
mailing list