Small Sample Properties of Bootstrap

Abstract

The Boostrap method is a nonparametric statistical technique for estimating the sampling distribution of estimators of unknown parameters. While the asymptotic theory for bootstrap is well established, this thesis investigates the behavior of the bootstrap for small sample sizes. For the exponential distribution and for normal linear regression the bootstrap estimates of the parameters and variances are compared with the theoretical sampling distributions. The small sample properties of bootstrap confidence intervals using the percentile method and the bias-corrected percentile method are also investigated. Keywords: Exponential distributions, Computerized simulation, Fortran, Subroutines.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1988
Accession Number
ADA202187

Entities

People

  • Stefan Bernhardt

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Computer Programming
  • Computer Programs
  • Computers
  • Estimators
  • Mainframe Computers
  • Mathematics
  • Normal Distribution
  • Operations Research
  • Probability
  • Probability Density Functions
  • Probability Distributions
  • Random Variables
  • Sampling
  • Simulations
  • Statistical Algorithms
  • Statistics
  • Validation

Fields of Study

  • Mathematics

Readers

  • Regression Analysis.
  • Statistical inference.