Ancillary Statistic

In statistics, an ancillary statistic is a statistic whose sampling distribution does not depend on the parameters of the underlying population's probability distribution. An ancillary statistic is a pivotal quantity (function of observations whose distribution does not depend on parameters) that is also a statistic (computed in terms of observations, not depending on any unobserved quantities). They can be used to construct prediction intervals.

This concept was introduced by the statistical geneticist Sir Ronald Fisher.