By Njesa Totty (Oregon State University)
As statistical computing has become an increasingly prevalent component of introductory statistics courses, so too has the use of the bootstrap. Reasons for this include its ability to help students learn statistical inference for a variety of settings, a goal stated by the Guidelines for Assessment and Instruction in Statistics Education (GAISE) for introductory statistics courses. While bootstrapping is a powerful tool, it requires that users validate a set of important assumptions before the results can be
considered valid and trustworthy. When these assumptions are overlooked, the usefulness of the bootstrap may be overinflated, causing controversy as discussed by Hayden (2019) and incorrect conclusions may be reached. We discuss why these assumptions are so important for valid conclusions to be made and introduce a new R package, bootEd and compare it with other packages. This package was
designed to help students and teachers of introductory statistics courses implement bootstrap methods easily, without overlooking these important assumptions.
Tim Hesterberg (2015). resample: Resampling Functions. R package version 0.4. https://CRAN.R-
Angelo Canty and Brian Ripley (2021). boot: Bootstrap R (S-Plus) Functions. R package version 1.3-27.
Neil A. Weiss (2016). wBoot: Bootstrap Methods. R package version 1.0.3. https://CRAN.R-
S original, from StatLib and by Rob Tibshirani. R port by Friedrich Leisch. (2019). bootstrap: Functions for
the Book ""An Introduction to the Bootstrap"". R package version 2019.6. https://CRAN.R-
R. Pruim, D. T. Kaplan and N. J. Horton. The mosaic Package: Helping Students to 'Think with Data' Using
R (2017). The R Journal, 9(1):77-102.
Robert W. Hayden (2019) Questionable Claims for Simple Versions of the Bootstrap, Journal of Statistics
Education, 27:3, 208-215, DOI: 10.1080/10691898.2019.1669507