The metafor Package

A Meta-Analysis Package for R

User Tools

Site Tools


tips:comp_two_independent_estimates

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
tips:comp_two_independent_estimates [2019/05/22 08:42]
Wolfgang Viechtbauer
tips:comp_two_independent_estimates [2019/05/22 08:54] (current)
Wolfgang Viechtbauer
Line 1: Line 1:
 ===== Comparing Estimates of Independent Meta-Analyses or Subgroups ===== ===== Comparing Estimates of Independent Meta-Analyses or Subgroups =====
  
-Suppose we have summary estimates (e.g., estimated average effects) obtained from two independent meta-analyses or subgroups of studies and we want to test whether the estimates are different from each other. A Wald-type test can be used for this purpose. Alternatively,​ one could run a single meta-regression model including all studies and using a dichotomous moderator to distinguish the two sets. Both approaches are conceptually very similar with a subtle difference that will be illustrated below with an example.+Suppose we have summary estimates (e.g., estimated average effects) obtained from two independent meta-analyses or two subgroups of studies ​within the same meta-analysis ​and we want to test whether the estimates are different from each other. A Wald-type test can be used for this purpose. Alternatively,​ one could run a single meta-regression model including all studies and using a dichotomous moderator to distinguish the two sets. Both approaches are conceptually very similar with a subtle difference that will be illustrated below with an example.
  
 ==== Data Preparation ==== ==== Data Preparation ====
Line 49: Line 49:
 </​code>​ </​code>​
  
-We can now compare the two estimates (i.e., the estimated average log risk ratios) by feeding them back to the ''​rma()''​ function and using the variable to distinguish the two estimates as a moderator. We use a fixed-effects model, because the (residual) heterogeneity within each subset has already been accounted for by fitting random-effects ​model above.+We can now compare the two estimates (i.e., the estimated average log risk ratios) by feeding them back to the ''​rma()''​ function and using the variable to distinguish the two estimates as a moderator. We use a fixed-effects model, because the (residual) heterogeneity within each subset has already been accounted for by fitting random-effects ​models ​above.
 <code rsplus> <code rsplus>
 rma(estimate,​ sei=stderror,​ mods = ~ meta, method="​FE",​ data=dat.comp,​ digits=3) rma(estimate,​ sei=stderror,​ mods = ~ meta, method="​FE",​ data=dat.comp,​ digits=3)
Line 81: Line 81:
 -1.395 -1.395
 </​code>​ </​code>​
-This is the same value as obtained above.+This is the same value that we obtained above.
  
 ==== Meta-Regression with All Studies ==== ==== Meta-Regression with All Studies ====
  
-Now let's take a different approach, fitting a meta-regression model using all studies:+Now let's take a different approach, fitting a meta-regression model with ''​alloc''​ as a categorical moderator based on all studies:
 <code rsplus> <code rsplus>
 rma(yi, vi, mods = ~ alloc, data=dat, digits=3) rma(yi, vi, mods = ~ alloc, data=dat, digits=3)
tips/comp_two_independent_estimates.txt ยท Last modified: 2019/05/22 08:54 by Wolfgang Viechtbauer