Skip to main content

Table 5 How does the degree of treatment-related risk influence the statistical power of the subgroup analysis? *

From: Multivariable risk prediction can greatly enhance the statistical power of clinical trial subgroup analysis

Annual Risk of Treatment-Related Adverse Events

Conventional "One-RF-at-a-Time" Subgroup Comparison*

Multivariable Risk Stratified Analysis*

(Events per 1000 patient-years)

Statistical Power †

1

6%

39%

2

11%

59%

3

21%

83%

4

28%

92%

  1. * There are 6 risk factors (RF's) that each have a prevalence of 25% and a relative risk of 2, and the 5-year CER for those without any risk factors is .75% (see Table 1 and Figure).
  2. † Statistical subgroup comparisons tests the power to detect whether the treatment's relative benefit varies as a function of the presence of the RF (for conventional subgroup analysis) or the risk score (for the multivariable risk-stratified analysis)
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us