The Bootstrap Method
摘要
In this chapter, we will learn how to estimate the standard error of an estimate and how to construct confidence intervals for a parameter of interest. Both problems can be solved by the bootstrap method, which was inspired by the jackknife. The bootstrap, introduced in 1979 by Bradley Efron, is a general simulation-based method for measuring the uncertainty of estimates, in particular, for estimating their standard errors and constructing confidence intervals. Its beauty lies in its simplicity and universality: the bootstrap is fully automatic, requires no theoretical calculations, and is always available.