Skip to main content

Table 1 Significance level for the Begg and Mazumdar test for publication bias: Small meta-analyses*

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

 

Level

 

[% selected for inclusion, bias]

Range of variances

Large†

Small‡

Treatment effect (δ)

  

.0

1.72%

3.96%

 

[100%,.00]

[100%,.00]

.5

1.82%

4.36%

 

[100%,.00]

[100%,.00]

1.0

1.86%

4.30%

 

[100%,.00]

[100%,.00]

1.5

1.90%

3.68%

 

[100%,.00]

[100%,.00]

2.0

1.82%

3.58%

 

[100%,.00]

[100%, -.00]

2.5

1.54%

4.48%

 

[100%,.00]

[100%,.00]

3.0

1.74%

4.24%

 

[100%,.00]

[100%, -.00]

  1. *k = 25 studies; nominal significance level 0.05.
  2. †v = 0.1, 1.0, 10.0, ‡v = 0.5, 1.0, 2.0.
  3. Values deviating significantly from the nominal level 5.00% over the 5000 simulations (using a 5% level in the binomial test) are typed in boldface.
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us