Glossary // Glossary term Technical
Statistical significance
A conventional label for a result whose p-value falls below a pre-set threshold, often 0.05. The p-value indicates how incompatible the data are with a specified statistical model, usually one of no effect; it does not measure the probability that a hypothesis is true or the size or importance of an effect. The American Statistical Association has cautioned against basing conclusions on whether a threshold was crossed, and a non-significant result is not evidence that an effect is absent. How one could reason about recording a catharsis-like change of state: signals, features, inference and context, baselines, self-report, error costs and ethics, and why every step stays uncertain. Nothing on this site measures anyone. Every public claim on this site with its type, evidence level, confidence, sources and review date, and an appraisal of each reference. How claims are graded, how art is kept apart from evidence, and how to report a problem. The works the definition rests on, with the level of evidence each was appraised at. (2016). The ASA statement on p-values: Context, process, and purpose. doi:10.1080/00031305.2016.1154108 Cited for the principles that a p-value does not measure the probability that a hypothesis is true or the size of an effect, and that conclusions should not rest only on crossing a threshold. An expert consensus statement, not an empirical study. (2014). The new statistics: Why and how. doi:10.1177/0956797613504966 Supports recommendations to report effect sizes with confidence intervals rather than rely on null-hypothesis significance testing. A position shared by many methodologists but not universally; it is guidance, not a test.Where the site uses it
Studies behind it