Skip to main content

Table 3 Comparison of power for the main treatment effect with power for interaction test, using the population average model (GEE)

From: Testing for heterogeneity among the components of a binary composite outcome in a clinical trial

 

OR1 = 0.65

OR1 = 0.65

OR1 = 0.70

OR1 = 0.70

OR1 = 0.75

OR1 = 0.75

OR2

Treatment Effect

Heterogeneity Test

Treatment Effect

Heterogeneity Test

Treatment Effect

Heterogeneity Test

0.65

>99.9

5.3

-

-

-

-

0.70

99.9

8.1

99.4

5.0

-

-

0.75

99.6

17.9

98.2

8.3

95.7

5.5

0.80

98.2

33.4

95.7

16.7

89.8

8.3

0.85

95.5

51.1

89.5

30.5

81.5

16.0

0.90

90.7

67.8

81.6

44.1

68.7

28.6

0.95

82.2

80.7

70.4

63.5

55.5

43.7

1.00

70.7

89.9

57.8

78.8

41.5

58.9

1.05

57.7

95.0

42.9

86.3

28.2

72.4

1.10

44.6

97.8

30.2

92.8

18.9

82.4

1.15

31.3

99.0

19.6

96.8

11.3

90.5

1.20

21.5

99.7

8.1

98.3

7.2

94.8