The metafor Package

A Meta-Analysis Package for R

User Tools

Site Tools

analyses:stijnen2010

Differences

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

Link to this comparison view

Both sides previous revisionPrevious revision
analyses:stijnen2010 [2021/10/22 14:45] – Wolfgang Viechtbaueranalyses:stijnen2010 [2022/08/03 11:22] (current) – Wolfgang Viechtbauer
Line 13: Line 13:
 dat dat
 </code> </code>
-(I copy the dataset into ''dat'', which is a bit shorter and therefore easier to type further below). The contents of the dataset are: +(I copy the dataset into ''dat'', which is a bit shorter and therefore easier to type further below). The contents of the dataset are:
 <code output> <code output>
    study         author year ai n1i ci n2i    study         author year ai n1i ci n2i
Line 48: Line 48:
 H^2 (total variability / sampling variability):  3.85 H^2 (total variability / sampling variability):  3.85
  
-Test for Heterogeneity: +Test for Heterogeneity:
 Q(df = 17) = 72.166, p-val < .001 Q(df = 17) = 72.166, p-val < .001
  
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -3.302    0.238  -13.883    <.001   -3.768   -2.836      *** +  -3.302    0.238  -13.883    <.001   -3.768   -2.836      ***
  
 --- ---
Line 82: Line 82:
 H^2 (total variability / sampling variability):  1.60 H^2 (total variability / sampling variability):  1.60
  
-Test for Heterogeneity: +Test for Heterogeneity:
 Q(df = 17) = 23.671, p-val = 0.129 Q(df = 17) = 23.671, p-val = 0.129
  
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -4.260    0.259  -16.457    <.001   -4.768   -3.753      *** +  -4.260    0.259  -16.457    <.001   -4.768   -3.753      ***
  
 --- ---
Line 116: Line 116:
 H^2 (total variability / sampling variability):  4.49 H^2 (total variability / sampling variability):  4.49
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 17) = 69.103, p-val < .001 Wld(df = 17) = 69.103, p-val < .001
 LRT(df = 17) = 85.284, p-val < .001 LRT(df = 17) = 85.284, p-val < .001
Line 122: Line 122:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -3.496    0.257  -13.605    <.001   -4.000   -2.993      *** +  -3.496    0.257  -13.605    <.001   -4.000   -2.993      ***
  
 --- ---
Line 149: Line 149:
 H^2 (total variability / sampling variability):  2.27 H^2 (total variability / sampling variability):  2.27
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 17) = 16.145, p-val = 0.514 Wld(df = 17) = 16.145, p-val = 0.514
 LRT(df = 17) = 37.990, p-val = 0.002 LRT(df = 17) = 37.990, p-val = 0.002
Line 155: Line 155:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -4.812    0.355  -13.537    <.001   -5.509   -4.115      *** +  -4.812    0.355  -13.537    <.001   -5.509   -4.115      ***
  
 --- ---
Line 187: Line 187:
 H^2 (total variability / sampling variability):  1.04 H^2 (total variability / sampling variability):  1.04
  
-Test for Heterogeneity: +Test for Heterogeneity:
 Q(df = 16) = 15.812, p-val = 0.466 Q(df = 16) = 15.812, p-val = 0.466
  
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -0.980    0.243   -4.027    <.001   -1.458   -0.503      *** +  -0.980    0.243   -4.027    <.001   -1.458   -0.503      ***
  
 --- ---
Line 223: Line 223:
 H^2 (total variability / sampling variability):  1.70 H^2 (total variability / sampling variability):  1.70
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 16) = 11.866, p-val = 0.753 Wld(df = 16) = 11.866, p-val = 0.753
 LRT(df = 16) = 28.609, p-val = 0.027 LRT(df = 16) = 28.609, p-val = 0.027
Line 229: Line 229:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -1.353    0.351   -3.855    <.001   -2.041   -0.665      *** +  -1.353    0.351   -3.855    <.001   -2.041   -0.665      ***
  
 --- ---
Line 245: Line 245:
 Since the likelihood for studies with zero events is flat, such studies are automatically dropped by the ''rma.glmm()'' function (i.e., ''drop00=TRUE'' by default for the ''rma.glmm()'' function). Since the likelihood for studies with zero events is flat, such studies are automatically dropped by the ''rma.glmm()'' function (i.e., ''drop00=TRUE'' by default for the ''rma.glmm()'' function).
  
-Finally, using the approximation to the exact likelihood, we can fit the same model with: +Finally, using the approximation to the exact likelihood, we can fit the same model with:
 <code rsplus> <code rsplus>
 res <- rma.glmm(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat, model="CM.AL") res <- rma.glmm(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat, model="CM.AL")
Line 259: Line 259:
 H^2 (total variability / sampling variability):  1.61 H^2 (total variability / sampling variability):  1.61
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 16) = 11.115, p-val = 0.802 Wld(df = 16) = 11.115, p-val = 0.802
 LRT(df = 16) = 27.392, p-val = 0.037 LRT(df = 16) = 27.392, p-val = 0.037
Line 265: Line 265:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -1.303    0.339   -3.847    <.001   -1.966   -0.639      *** +  -1.303    0.339   -3.847    <.001   -1.966   -0.639      ***
  
 --- ---
Line 287: Line 287:
 dat dat
 </code> </code>
-(I copy the dataset into 'dat', which is a bit shorter and therefore easier to type further below). The contents of the dataset are: +(I copy the dataset into 'dat', which is a bit shorter and therefore easier to type further below). The contents of the dataset are:
 <code output> <code output>
   study          authors year x1i   t1i x2i   t2i   study          authors year x1i   t1i x2i   t2i
Line 321: Line 321:
 H^2 (total variability / sampling variability):  4.06 H^2 (total variability / sampling variability):  4.06
  
-Test for Heterogeneity: +Test for Heterogeneity:
 Q(df = 8) = 36.384, p-val < .001 Q(df = 8) = 36.384, p-val < .001
  
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-   1.468    0.243    6.051    <.001    0.992    1.943      *** +   1.468    0.243    6.051    <.001    0.992    1.943      ***
  
 --- ---
Line 354: Line 354:
 H^2 (total variability / sampling variability):  4.07 H^2 (total variability / sampling variability):  4.07
  
-Test for Heterogeneity: +Test for Heterogeneity:
 Q(df = 8) = 25.427, p-val = 0.001 Q(df = 8) = 25.427, p-val = 0.001
  
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-   0.981    0.326    3.009    0.003    0.342    1.620       ** +   0.981    0.326    3.009    0.003    0.342    1.620       **
  
 --- ---
Line 386: Line 386:
 H^2 (total variability / sampling variability):  3.62 H^2 (total variability / sampling variability):  3.62
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 8) = 36.384, p-val < .001 Wld(df = 8) = 36.384, p-val < .001
 LRT(df = 8) = 38.330, p-val < .001 LRT(df = 8) = 38.330, p-val < .001
Line 392: Line 392:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-   1.401    0.231    6.063    <.001    0.948    1.853      *** +   1.401    0.231    6.063    <.001    0.948    1.853      ***
  
 --- ---
Line 419: Line 419:
 H^2 (total variability / sampling variability):  4.14 H^2 (total variability / sampling variability):  4.14
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 8) = 25.427, p-val = 0.001 Wld(df = 8) = 25.427, p-val = 0.001
 LRT(df = 8) = 44.488, p-val < .001 LRT(df = 8) = 44.488, p-val < .001
Line 425: Line 425:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-   0.849    0.330    2.572    0.010    0.202    1.497        * +   0.849    0.330    2.572    0.010    0.202    1.497        *
  
 --- ---
Line 455: Line 455:
 H^2 (total variability / sampling variability):  1.26 H^2 (total variability / sampling variability):  1.26
  
-Test for Heterogeneity: +Test for Heterogeneity:
 Q(df = 8) = 9.698, p-val = 0.287 Q(df = 8) = 9.698, p-val = 0.287
  
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -0.396    0.227   -1.747    0.081   -0.841    0.048        . +  -0.396    0.227   -1.747    0.081   -0.841    0.048        .
  
 --- ---
-Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 +Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
 </code> </code>
 And the estimated average log incidence rate ratio (i.e., $\hat{\mu} = -0.396$) can again be back-transformed through exponentiation: And the estimated average log incidence rate ratio (i.e., $\hat{\mu} = -0.396$) can again be back-transformed through exponentiation:
Line 489: Line 489:
 H^2 (total variability / sampling variability):  1.35 H^2 (total variability / sampling variability):  1.35
  
-Tests for Heterogeneity: +Tests for Heterogeneity:
 Wld(df = 8) =  9.698, p-val = 0.287 Wld(df = 8) =  9.698, p-val = 0.287
 LRT(df = 8) = 11.602, p-val = 0.170 LRT(df = 8) = 11.602, p-val = 0.170
Line 495: Line 495:
 Model Results: Model Results:
  
-estimate       se     zval     pval    ci.lb    ci.ub           +estimate       se     zval     pval    ci.lb    ci.ub 
-  -0.476    0.238   -2.004    0.045   -0.942   -0.010        * +  -0.476    0.238   -2.004    0.045   -0.942   -0.010        *
  
 --- ---
analyses/stijnen2010.txt · Last modified: 2022/08/03 11:22 by Wolfgang Viechtbauer