A trial of a new antidiabetic drug reports p = 0.08 for the primary endpoint, and the investigators conclude there is no significant benefit. A reviewer notes the trial enrolled only 40 patients per arm. The single most effective step to reduce the chance of missing a true treatment effect in a repeat study is:
- A Decrease the significance level to 0.01
- B Raise the level of the null hypothesis
- C Increase the sample size ✓
- D Use a one-tailed test instead of a two-tailed test
Correct answer: C. Increase the sample size
Explanation
Power, the ability to detect a real difference, equals 1 minus beta and depends chiefly on sample size, effect size and variability. With only 40 patients per arm the study was likely underpowered, so beta was high. Increasing sample size reduces the standard error and raises power. Lowering alpha to 0.01 further decreases power, and alpha cannot be raised above its conventional 0.05 without inflating false positives.
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.