In inferential statistics, the null hypothesis is a general

statementor default position that there isno relationship between two measured phenomena, orno association among groups.

Testing (accepting, approving, rejecting, or disproving) the null hypothesis — and thus concluding that there are or are not grounds for believing that there is a relationship between two phenomena (e.g. that a potential treatment has a measurable effect) — is a

central task in the modern practice of science; the field ofstatistics gives precise criteria for rejecting a null hypothesis.

The null hypothesis is

generally assumed to be true until evidence indicates otherwise.