docs.daveops.net

Snippets for yer computer needs

Statistics

Statistical hypothesis testing

Null hypothesis - general statement that nothing is happening.

Errors

Type 1 - False positive. The mistaken rejection of an actually true null hypothesis. β€œAn innocent person is convicted.”

Type 2 - False negative. The mistaken acceptance of an actually false null hypothesis. β€œA guilty person is not convicted.”

A crossover error rate (CER) is the point at which both types are equal. A lower CER means something is more accurate.