Exploring the Limits of Bootstrap

Explores the application of bootstrap to problems that place unusual demands on the method. The bootstrap method, introduced by Bradley Efron in 1973, is a nonparametric technique for inferring the distribution of a statistic derived from a sample. Most of the papers were presented at a special meeting sponsored by the Institute of Mathematical Statistics and the Interface Foundation in May, 1990. Partial table of contents:

GENERAL PRINCIPLES OF THE BOOTSTRAP.

On the Bootstrap of M-Estimators and Other Statistical Functionals(M. Arcones & E. Gine).

Bootstrapping Markov Chains (K. Athreya & C. Fuh).

Six Questions Raised by the Bootstrap (B. Efron).

Efficient Bootstrap Simulation (P. Hall).

Bootstrapping Signs (R. LePage).

Bootstrap Bandwidth Selection (J. Marron).

APPLICATIONS OF THE BOOTSTRAP.

A Generalized Bootstrap (E. Bedrick & J. Hill).

Bootstrapping Admissible Linear Model Selection Procedures (D.Brownstone).

A Hazard Process for Survival Analysis (J. Hsieh).

A Nonparametric Density Estimation Based Resampling Algorithm (M.Taylor & J. Thompson).

Nonparametric Rank Estimation Using Bootstrap Resampling andCanonical Correlation Analysis (X. Tu, et al.).

Index.

Raoul LePage is the editor of Exploring the Limits of Bootstrap, published by Wiley. Lynne Billard is an American statistician and professor at the University of Georgia, known for her statistics research, leadership, and advocacy for women in science.