Term
Statistical significance
A pre-specified statistical threshold showing a result is unlikely to be chance alone; necessary for a confirmatory claim, not sufficient for a meaningful one.
A trial's primary analysis is planned in advance: the comparison, the statistical test and the threshold (commonly p below 0.05). Crossing that threshold means a result this extreme would be unlikely if the drug did nothing. It does not mean the effect is large, durable or clinically worthwhile; a big trial can make a trivial difference significant.
Grading on this site asks whether the primary comparison was statistically significant in the favorable direction as pre-specified, and separately whether the endpoint and effect are worth having. Both questions matter; only the first is answered by a p-value.
Related terms