'Univariate vs Multivariate meta-regression in metafor
I'm performing a meta-analysis using the package metafor. My data set has 2 moderators. I have performed univariate meta-regressions for each moderator, using these codes:
Univariate meta-regression model. Moderator: LOCATION
resMeta <- rma(measure="IR",xi=xi, ti=ti, mods = ~ factor(locat), data=metaAAS)
Univariate meta-regression model. Moderator: SUBPOPULATION
resMeta <- rma(measure="IR",xi=xi, ti=ti, mods = ~ (factor(pop), data=metaAAS)
Now I need to perform a multivariate meta-regression. Is that correct to simply add both moderators to that same function (below)?
resMeta <- rma(measure="IR",xi=xi, ti=ti, mods = ~ factor(locat)+factor(pop), data=metaAAS)
The code works fine, I just don't know if is technically correct to describe these results as a multivariate meta-regression.
Thank you.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|