Index: The Book of Statistical ProofsGeneral TheoremsFrequentist statisticsHypothesis testing ▷ Statistical test

Definition: Let $y$ be a set of measured data. Then, a statistical hypothesis test consists of the following:

Procedurally, the statistical hypothesis test works as follows:

  • Given the null hypothesis $H_0$ and the significance level $\alpha$, a critical value $t_\mathrm{crit}$ is determined which partitions the set of possible values of $T(Y)$ into “acceptance region” and “rejection region”.

  • Then, the observed test statistic $t_\mathrm{obs} = T(y)$ is calculated from the actually measured data $y$. If it is in the rejection region, $H_0$ is rejected in favor of $H_1$. Otherwise, the test fails to reject $H_0$.

 
Sources:

Metadata: ID: D130 | shortcut: test | author: JoramSoch | date: 2021-03-19, 14:36.