Statistical significance

Statistical significance means a result is unlikely to be due to chance alone. It does not tell you whether the result is large or important.

Definition from Shrinktionary, reviewed by Shariq Refai, MD, MBA, FAPA (last reviewed 2026-06-26). Shrinktionary is the network's language layer and carries the canonical short definition; this page adds the research-context detail below. Full definition on Shrinktionary →

Statistical significance answers one narrow question: could this result be a coincidence of sampling? If the answer is probably not, the result is called significant. That is all the term means. It says nothing about whether the effect is large, useful, or meaningful to a patient.

News coverage often treats "statistically significant" as proof that a treatment works well. That's a misreading. A significant result in a very large trial can describe an effect too small for any patient to notice.

A trial of 5,000 people finds a treatment lowers anxiety scores by half a point on a 21-point scale, with a significant p-value. The result is real, but half a point is unlikely to change how anyone feels.

Significance depends heavily on sample size. Big studies can make trivial effects significant. Small studies can miss real effects and call them non-significant. Always pair statistical significance with clinical significance, which asks whether the effect is big enough to matter.