Research brief · 2026-09-09
How Small Is Too Small? Sample Size, Explained
How many people does a study need? There is no fixed number. Sample size is about matching the sample to the size of the effect being chased and how much variability surrounds it. A large, consistent effect can be detected in a small group. A small effect, or a noisy outcome, needs many more people before the signal separates from the noise.
A 1999 paper in the Journal of Bone and Mineral Research by Murphy and colleagues shows the small end. MK-677, also called ibutamoren, is a growth hormone secretagogue that is not approved as a medicine. The researchers tested it in healthy elderly adults in groups of just 10 to 12 people for two weeks, and urinary markers of bone turnover still rose significantly versus placebo, because the biochemical effect was large and consistent. The same paper then scaled up to 50 and then 105 people, and each step let it catch smaller marker changes.
A 2004 trial in the Journal of the American Geriatrics Society by Bach and colleagues shows what happens when the outcome gets noisier. It tested MK-677 in 161 older adults recovering from hip fracture for six months. IGF-1 rose 84 percent on the drug versus 17 percent on placebo, with non-overlapping confidence intervals. But functional recovery, measured with physical performance tests, showed no significant difference despite favorable trends. The authors wrote that those measures may not be responsive enough for a trial that size.
At the opposite extreme, the SELECT trial of semaglutide, a prescription medication, enrolled 17,604 people precisely because the effect it needed to detect was about 1.5 percentage points. An underpowered study fails both ways: it can miss a real effect, and it can produce a dramatic-looking result purely because small samples generate extreme estimates by chance. What these studies do not tell you is whether a larger MK-677 trial would find a functional benefit, or whether marker changes ever become fewer fractures. Decisions about any of these compounds belong with a physician. Sources are listed below.
Sources
- Murphy MG et al., Oral administration of the growth hormone secretagogue MK-677 increases markers of bone turnover in healthy and functionally impaired elderly adults (n=187)
- Journal of Bone and Mineral Research, 1999
- Bach MA et al., The effects of MK-0677, an oral growth hormone secretagogue, in patients with hip fracture (n=161)
- Journal of the American Geriatrics Society, 2004
- Lincoff AM et al., Semaglutide and cardiovascular outcomes in obesity without diabetes (SELECT trial, n=17,604)
- New England Journal of Medicine, 2023
Peptide Proof reports what studies found. We do not give medical advice, dosing guidance, or treatment recommendations.