What Teachers Should Know About the Bootstrap: Resampling in the Undergraduate Statistics Curriculum

TLDR

Bootstrapping offers great potential in statistics education and practice, yet it carries subtle pitfalls that can lead to errors. The article aims to deepen understanding of bootstrap methods, clarify their strengths and limitations, and address pedagogical concerns. The study finds that nonparametric bootstrapping with percentile confidence intervals underperforms t‑intervals for small samples but outperforms them for larger samples. Supplementary materials are available online; the article was received December 2014 and revised August 2015.

Abstract

Bootstrapping has enormous potential in statistics education and practice, but there are subtle issues and ways to go wrong. For example, the common combination of nonparametric bootstrapping and bootstrap percentile confidence intervals is less accurate than using t-intervals for small samples, though more accurate for larger samples. My goals in this article are to provide a deeper understanding of bootstrap methods—how they work, when they work or not, and which methods work better—and to highlight pedagogical issues. Supplementary materials for this article are available online.[Received December 2014. Revised August 2015]