The metafor Package

A Meta-Analysis Package for R

User Tools

Site Tools

tips:model_selection_with_glmulti_and_mumin

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
tips:model_selection_with_glmulti_and_mumin [2022/08/03 11:33] – Wolfgang Viechtbauertips:model_selection_with_glmulti_and_mumin [2022/08/09 05:15] – Wolfgang Viechtbauer
Line 1: Line 1:
 ===== Model Selection using the glmulti and MuMIn Packages ===== ===== Model Selection using the glmulti and MuMIn Packages =====
  
-Information-theoretic approaches provide methods for model selection and (multi)model inference that differ quite a bit from more traditional methods based on null hypothesis testing (e.g., Anderson, 2007; Burnham & Anderson, 2002). These methods can also be used in the meta-analytic context when model fitting is based on likelihood methods. Below, I illustrate how to use the metafor package in combination with the [[https://cran.r-project.org/package=glmulti|glmulti]] and [[https://cran.r-project.org/package=MuMIn|MuMIn]] packages that provides the necessary functionality for model selection and multimodel inference using an information-theoretic approach.+Information-theoretic approaches provide methods for model selection and (multi)model inference that differ quite a bit from more traditional methods based on null hypothesis testing (e.g., Anderson, 2007; Burnham & Anderson, 2002). These methods can also be used in the meta-analytic context when model fitting is based on likelihood methods. Below, I illustrate how to use the metafor package in combination with the [[https://cran.r-project.org/package=glmulti|glmulti]] and [[https://cran.r-project.org/package=MuMIn|MuMIn]] packages that provide the necessary functionality for model selection and multimodel inference using an information-theoretic approach.
  
 ==== Data Preparation ==== ==== Data Preparation ====
Line 172: Line 172:
  
 If we do want to make inferences about the various predictors, we may want to do so not in the context of a single model that is declared to be "best", but across all possible models (taking their relative weights into consideration). Multimodel inference can be used for this purpose. To get the glmulti package to handle ''rma.uni'' objects, we must register a ''getfit'' method for such objects. The necessary code for this comes with the metafor package, but it first needs to be evaluated with: If we do want to make inferences about the various predictors, we may want to do so not in the context of a single model that is declared to be "best", but across all possible models (taking their relative weights into consideration). Multimodel inference can be used for this purpose. To get the glmulti package to handle ''rma.uni'' objects, we must register a ''getfit'' method for such objects. The necessary code for this comes with the metafor package, but it first needs to be evaluated with:
-<code>+<code rsplus>
 eval(metafor:::.glmulti) eval(metafor:::.glmulti)
 </code> </code>
tips/model_selection_with_glmulti_and_mumin.txt · Last modified: 2022/10/13 06:07 by Wolfgang Viechtbauer