Skip to main content

Table 4 Number (%) of scenarios exceeding the 5% alpha threshold according to the number of correctly analyzed CRTs

From: Warnings on the inclusion of cluster randomized trials in meta-analysis: results of a simulation study

Condition (total number of scenarios)

Correctly analyzed CRTs

None

Half

All

All studies were CRTs

ā€ƒOverall (n = 243 each)

195 (80.3%)

177 (72.8%)

6 (2.5%)

ā€ƒ4 CRT of 4 studies (n = 81 each)

75 (92.6%)

66 (81.5%)

3 (3.7%)

ā€ƒ8 CRT of 8 studies (n = 81 each)

63 (77.8%)

57 (70.4%)

3 (3.7%)

ā€ƒ12 CRT of 12 studies (n = 81 each)

57 (70.4%)

54 (66.7%)

0 (0.0%)

Half of the studies were CRTs

ā€ƒOverall (n = 243 each)

78 (32.1%)

21 (8.6%)

0 (0.0%)

ā€ƒ2 CRT of 4 studies (n = 81 each)

42 (51.9%)

15 (18.5%)

0 (0.0%)

ā€ƒ4 CRT of 8 studies (n = 81 each)

21 (25.9%)

3 (3.7%)

0 (0.0%)

ā€ƒ6 CRT of 12 studies (n = 81 each)

15 (18.5%)

3 (3.7%)

0 (0.0%)

One study was a CRT

ā€ƒOverall (n = 243 each)

9 (3.7%)

-

0 (0.0%)

ā€ƒ1 CRT of 4 studies (n = 81 each)

9 (11.1%)

-

0 (0.0%)

ā€ƒ1 CRT of 8 studies (n = 81 each)

0 (0.0%)

-

0 (0.0%)

ā€ƒ1 CRT of 12 studies (n = 81 each)

0 (0.0%)

-

0 (0.0%)