Skip to main content

Table 4 Power for the Begg and Mazumdar test for publication bias: Large meta-analyses*

From: Improving the error rates of the Begg and Mazumdar test for publication bias in fixed effects meta-analysis

 

Power

 

[% selected for inclusion, bias]

Selection strength

Strong**

Moderate***

Range of variances

Large†

Small ‡

Large†

Small‡

Treatment effect (δ)

    

.0

99%

61%

88%

38%

 

[36%,.34]

[36%,.74]

[56%,.24]

[56%,.54]

.5

99%

59%

77%

31%

 

[53%,.16]

[52%,.54]

[74%,.09]

[72%,.34]

1.0

94%

50%

54%

21%

 

[64%,.07]

[67%,.36]

[82%,.04]

[84%,.19]

1.5

85%

35%

35%

12%

 

[71%,.04]

[79%,.23]

[86%,.02]

[92%,.10]

2.0

71%

22%

21%

7%

 

[77%,.03]

[88%,.13]

[90%,.02]

[96%,.05]

2.5

53%

12%

13%

5%

 

[81%,.02]

[93%,.07]

[92%,.01]

[98%,.03]

3.0

40%

7%

8%

5%

 

[85%,.02]

[96%,.04]

[94%,.01]

[99%,.01]

  1. *k = 75 studies; nominal significance level 0.05.
  2. **a = 1.5, ***a = 3.0.
  3. v = 0.1, 1.0, 10.0, ‡v = 0.5, 1.0, 2.0.