Fiducial inference was introduced in the first half of the 20th century by Fisher (1935) as a means to get a posterior-like distribution for a parameter without having to arbitrarily define a prior. While the method originally fell out of favor due to non-exactness issues in multivariate cases, the method has garnered renewed interest in the last decade. This is partly due to the development of generalized fiducial inference, which is a fiducial perspective on generalized confidence intervals: a method used to find approximate confidence distributions. In this chapter, we illuminate the usefulness of the fiducial philosophy, introduce the definition of a generalized fiducial distribution, and apply it to interesting, non-trivial inferential examples.

翻译：费歇尔推断由费歇尔（Fisher, 1935）在20世纪上半叶提出，旨在无需任意定义先验分布的情况下，为参数提供类似后验的分布。尽管该方法最初因在多变量情形下存在非精确性问题而失宠，但近十年来重新引起了学术界的关注。这在一定程度上可归因于广义费歇尔推断的发展——该方法从费歇尔推断视角出发研究广义置信区间，即用于寻找近似置信分布的一种技术。本章将阐明费歇尔推断哲学的实用性，给出广义费歇尔分布的定义，并将其应用于若干具有重要意义的非平凡推断实例中。