Significance test

From Glossary of Meteorology

significance test

A test of the reliability of estimate of statistical parameters.

Such tests proceed by assuming that the estimates are not significant and are those to be expected from sampling a particular population, and then, from the properties of the population, determining the probabilities of such occurrences. The hypothesis (that the estimates are not significant) is rejected only when an observational result is found to be significant, that is, when the obtained result belongs to an objectively specified unfavorable class (critical region or rejection region) having a fixed, small probability of occurrence in random samples from the hypothesized population. When the result falls in the acceptance region, it is not significant and the hypothesis cannot be rejected. The boundaries of the classes are set in such a way that the total probability (unity) is appropriately divided between them, say 0.95, 0.05 or 0.99, 0.01. The probability assigned to the critical region, commonly either 0.05 or 0.01, is called the significance level.
See chi- square test, Student's t-test, analysis of variance.

Copyright 2022 American Meteorological Society (AMS). For permission to reuse any portion of this work, please contact [email protected]. Any use of material in this work that is determined to be “fair use” under Section 107 of the U.S. Copyright Act (17 U.S. Code § 107) or that satisfies the conditions specified in Section 108 of the U.S.Copyright Act (17 USC § 108) does not require AMS’s permission. Republication, systematic reproduction, posting in electronic form, such as on a website or in a searchable database, or other uses of this material, except as exempted by the above statement, require written permission or a license from AMS. Additional details are provided in the AMS Copyright Policy statement.