ABCDELMNOPQRSTUVWXYZ
1
Calculating the review informatin size when effects are large
2
User-entered data
3
Threshold for small effect (MID) 0.02
Enter threshold as proportion
4
Threshold for moderate effect 0.05
Enter threshold as proportion
5
Threshold for large effect 0.09
Enter threshold as proportion
6
7
Baseline risk0.1
Enter baseline risk as proportion
8
Type I error (alpha)0.05
Enter type 1 error (typically 0.05)
9
Power0.8
Enter power power (typically 0.8)
10
11
Review size (total number of participants)200
12
13
The true risk difference must lie in the large range (i.e., be equal to Large + ∆)
14
Some possibilities for Large + ∆ based on the thresholds above:
15
16
Option 1Large + small effect (MID)0.11
17
Option 2Large + (Moderate - small effect (MID))0.12
18
Option 3Large + Moderate0.14
19
Option 4Large + (Large - small effect (MID))0.16
20
Option 5Large + (Large - Moderate)0.13
21
Option 6Large + Large0.18
22
23
Type in your assumed true risk difference0.11
Choose the scenario and enter the value
24
IMPORTANT: the recommended strategy is to specify an "assumed true risk difference" = Large + small effect (MID) (i.e. Scenario 1)
25
Results of RIS calculation
26
27
ThresholdSample size to rule outGRADE action
28
Small (MID)496Rate down
29
Moderate effect1,116Rate down
30
Large effect10,044Rate down
31
32
Summary GRADE imprecision ratingRate down three levels
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100