APA Dictionary of Psychology

in hypothesis testing, a set of procedures used to determine whether the differences between two groups or models are statistically significant (i.e., unlikely to arise solely from chance). In its most common form, significance testing is used to decide whether the null hypothesis of no effect should be rejected. A comparison of the probability statistic obtained from the test to the chosen significance level determines whether an observed effect may be due to chance variance and hence whether the null hypothesis is or is not likely to be correct. This approach may also be used to differentiate between two models that differ in terms of the number of parameters specified in them (as in multiple regression analysis).