Skip to main content

Table 3 Operating characteristics of two-step procedure for deciding whether or not to pool

From: Considerations for pooling real-world data as a comparator cohort to a single arm trial: a simulation study on assessment of heterogeneity

 

Rejection probability (comparison to SAT)

Response difference (%)

SAT response (%)

rwCC #1 response (%)

rwCC #2 response (%)

Pooling probabilitya

Conditional on pooling

If always pool

Expected when always pooling

Average when pooling

80

50

50

0.94 (0.0002)

0.85 (0.0001)

0.85 (0.0005)

30

30.01 (0.0001)

80

50

60

0.87 (0.0003)

0.70 (0.0002)

0.71 (0.0005)

25

24.94 (0.0001)

80

50

70

0.67 (0.0005)

0.50 (0.0003)

0.52 (0.0005)

20

19.68 (0.0001)

80

50

80

0.36 (0.0005)

0.27 (0.0005)

0.31 (0.0005)

15

13.96 (0.0001)

  1. aData is pooled when heterogeneity is not detected