power analysis
A statistical calculation that determines the sample size needed to detect a clinically meaningful treatment difference with specified confidence.
Full Definition
Power analysis is fundamental to cardiovascular trial design, calculating the minimum sample size required to detect a clinically meaningful treatment effect with adequate statistical power (typically 80% or 90%). The calculation requires specification of the primary endpoint, expected effect size, significance level (usually 0.05), and anticipated event rates or variability. In cardiovascular trials, power calculations often account for expected dropout rates, non-adherence, and crossover between treatment groups. Adaptive trial designs may include interim power re-assessments with possible sample size modifications. Underpowered studies risk failing to detect clinically important benefits, while overpowered studies may waste resources and unnecessarily expose participants to investigational treatments.
Usage
Usage note: Distinguish from statistical power (the probability); always specify assumptions used in calculations.
In Context
- "Power analysis determined that 3,200 patients would provide 90% power to detect a 20% reduction in MACE." — Study design rationale
- "The interim power analysis supported continuation without sample size modification." — Data monitoring committee report