Definition

Null hypothesis

The default assumption a statistical test tries to discredit — usually that there is no effect, no difference, or no relationship.

Classical significance testing works by contradiction: assume nothing is going on (the null, H0), compute how surprising the data would be under that assumption, and reject the null if the surprise (p-value) is extreme enough. The alternative hypothesis (H1) is what you actually suspect.

Failing to reject the null is not proof of no effect — absence of evidence is not evidence of absence, especially in small samples. Equivalence tests and well-powered designs exist precisely to make "no meaningful effect" a claim you can support.