Skip to main content

Table 9 Bootstrap results for the stopped trials based on ICON4 and RE01 in a two-stage design

From: Impact of lack-of-benefit stopping rules on treatment effect estimates of two-arm multi-stage (TAMS) trials with time to event outcome

  

I and D outcomes are OSa

I outcome is PFSb, D outcome is OSa

    

Estimated H R D for trials stopped at stage 1

  

Estimated H R D for trials stopped at stage 1

   

%

At interim point

After follow-up

  

At interim point

After follow-up

α 1 c

δ 1 d

e 1 e

%Stop

Mean (centiles)

%Bias

Mean (centiles)

%Bias

e 1 e

%Stop

Mean (centiles)

%Bias

Mean (centiles)

%Bias

a) ICON4 –

H R D (95% bootstrap CI): 0.82(0.67,0.99)

0.50

1.00

75

1

1.05(1.00,1.20)

28

0.98(0.81,1.18)

20

75

1

1.17(0.80,1.66)

43

0.91(0.73,1.16)

11

0.40

0.96

98

3

1.01(0.97,1.18)

23

0.99(0.86,1.21)

21

97

1

0.99(0.71,1.31)

21

0.94(0.76,1.15)

15

0.30

0.94

126

4

0.98(0.94,1.12)

20

1.01(0.88,1.18)

23

125

2

0.87(0.66,1.12)

6

0.97(0.84,1.18)

18

0.20

0.91

163

8

0.96(0.91,1.09)

17

0.97(0.88,1.10)

18

162

5

0.89(0.70,1.12)

9

0.96(0.82,1.13)

17

0.10

0.89

222

14

0.99(0.89,1.55)

21

0.91(0.68,1.10)

11

221

12

0.86(0.70,1.05)

5

0.96(0.82,1.13)

17

b) RE01 –

H R D (95% bootstrap CI): 0.75(0.60,0.93)

0.50

1.00

51

13

1.10(1.00,1.37)

47

0.96(0.76,1.21)

28

49

7

1.21(0.80,1.80)

61

1.11(0.77,1.56)

48

0.40

0.96

66

11

1.04(0.96,1.27)

39

0.91(0.74,1.16)

21

64

8

1.06(0.76,1.50)

41

0.97(0.69,1.37)

29

0.30

0.92

85

6

0.99(0.93,1.14)

32

0.92(0.77,1.14)

23

83

4

1.02(0.77,1.31)

36

0.91(0.71,1.22)

21

0.20

0.89

110

6

0.95(0.89,1.09)

27

0.90(0.77,1.06)

20

108

1

0.97(0.68,1.24)

29

0.93(0.69,1.23)

24

0.10

0.86

150

11

0.91(0.86,1.04)

21

0.88(0.72,0.95)

17

148

2

0.90(0.76,1.10)

20

0.86(0.73,1.05)

15

  1. aOverall survival;
  2. bprogression-free survival;
  3. cone-sided significance level at stage 1;
  4. dpredefined threshold at stage 1;
  5. ecumulative number of control arm events required at end of stage 1.