A pilot trial of a new antidiabetic drug fails to detect a real difference in HbA1c because it enrolled too few patients. Which single modification would most directly increase the statistical power of a repeat trial?

• A Raising the significance level from 0.05 to a smaller value
• B Using a one-tailed test where a two-tailed test was planned
• C Increasing the sample size ✓
• D Reporting odds ratios instead of relative risks

Explanation

Power is 1 minus beta, the probability of detecting a true effect when it exists. Increasing the sample size reduces the standard error, narrows confidence intervals and directly raises power. Making alpha stricter lowers the type I error threshold but further reduces power, so option A moves in the wrong direction. Switching to a one-tailed test inflates apparent significance and changes the hypothesis, while the choice of effect measure has no bearing on power.

Reference: Park's Textbook of Preventive and Social Medicine, 27th ed.

High-yield for: NEET PGINI-CETNExTFMGEUSMLEPLABMRCP

Written and medically reviewed by the StethoPrep medical team.