Skip to main content

Table 1 Sample layout of sensitivity analysis.

From: Current sample size conventions: Flaws, harms, and alternatives

  

Box#                          Observed difference in outcome rates (95% CI)

  

Expected

-2.8%

Intermediate

-1.4%

Null

0%

Observed

Low 3%

1                      -2.8

(-3.9 to -1.6)

2                      -1.4

(-2.7 to -0.03)

3                      0

(-1.5 to +1.5)

outcome rate

Expected 6.5%

4                      -2.8

(-4.8 to -0.8)

5                      -1.4

(-3.5 to +0.7)

6                      0

(-2.2 to +2.2)

in controls

High 12%

7                      -2.8

(-5.6 to +0.01)

8                      -1.4

(-4.3 to +1.5)

9                      0

(-2.9 to +2.9)

  1. Shown are possible study results with a given sample size (935 per group, based on the vitamin study discussed above [16]), for a yes or no outcome. Rows have differing assumptions concerning precision of the estimates, ranging from high precision (top row) to low precision (bottom row). For a continuous outcome, the rows would instead be for optimistic (small), expected, and pessimistic (large) standard deviations.
Back to article page

BMC Medicine

ISSN: 1741-7015

Contact us