Skip to main content

Table 2 Probability thresholds for evaluating statistical triggers at interim and final analyses

From: The ORVAC trial: a phase IV, double-blind, randomised, placebo-controlled clinical trial of a third scheduled dose of Rotarix rotavirus vaccine in Australian Indigenous infants to improve protection against gastroenteritis: a statistical analysis plan

Posterior/predictive

Decision

Threshold

Comment

Posterior

Win

0.97

Probability threshold to test that treatment difference is greater than zero

Predictive

Expected success

0.90

Proportion of successful trials must be greater than this threshold to claim expected success

Predictive

Futility

0.05

Proportion of successful trials must be in less than this threshold to claim futility

Predictive

Stop venous sampling

0.90

Proportion of successful trials must be greater than this threshold to stop venous sampling

Back to article page

Trials

ISSN: 1745-6215