Online Program Home
My Program

Abstract Details

Activity Number: 531 - SPEED: Statistical Computing: Methods, Implementation, and Application, Part 2
Type: Contributed
Date/Time: Wednesday, July 31, 2019 : 11:35 AM to 12:20 PM
Sponsor: Section for Statistical Programmers and Analysts
Abstract #307940
Title: Bootstrap in the Linear Model: a Comprehensive R Package
Author(s): Megan Heyman*
Companies: Rose-Hulman Institute of Technology
Keywords: R package; bootstrap; linear model

Since computation power has become more readily available, bootstrapping has become a mainstream statistical analysis tool and recently, even appears as a topic in most introductory statistics courses. Often, when the bootstrap is presented, it is implied that the technique is the original method proposed by Efron in 1979. However, there are many different forms of the bootstrap that an analyst could choose. The choice of bootstrap technique depends on what the user is willing to assume. For example, the wild bootstrap (Wu 1986) has weaker assumptions than Efron’s bootstrap.

The purpose of this R package is to provide a single platform to implement multiple forms of bootstrap in linear models. Although many of the forms of bootstrap appear in separate existing R packages, it appears that there is not a package which implements all types of bootstrap for inference in linear models. The syntax is aligned with the lm() function so that novice R users might easily implement the functions in analysis.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program