Chapter 16: Resampling Methods

William H. Beasley & Joseph L. Rodgers

Resampling methods Resampling is a statistical approach that relies on empirical analysis, based on the observed data, instead of asymptotic and parametric theory. The goal of resampling is to make an inferential decision, which is the same goal as that of a parametric statistical test such as the conventional t or analysis of variance (ANOVA). The difference is in how the goal is achieved. In this chapter, we will define and describe three resampling procedures: the permutation test, the jackknife, and the bootstrap. We place a strong emphasis on the bootstrap because it is the most flexible and most frequently used. We will describe both the concepts and the mechanisms that underlie resampling theory. In the course of this development, we hope that readers new to this area will begin to see ways of incorporating resampling methods into various aspects of their applied research, ways that allow them to address ...

Users without subscription are not able to see the full content on this title. Please, subscribe or login to access all content on this website.

• Buy The Book