Robust Statistical Estimation through Minimum Distance Using the Three-Parameter Weibull.

Abstract

A comparison was made between maximum likelihood and minimum distance estimation for the three-parameter Weibull distribution. Six estimation techniques were developed by using combinations of maximum likelihood and minimum distance estimation. The minimum distance methods were conducted using both the Anderson-Darling and Cramer-von Mises goodness of fit statistics. The estimators were tested by Monte Carlo simulations. For each set of parameters and sample size, 1000 data sets were generated and evaluated. Eight evaluation criteria, ranging from measuring the precision of estimating the population parameters to measuring the discrepancy between the estimated and population cumulative distribution functions (CDFs), were used. The robustness of the estimation techniques was tested by fitting Weibull CDFs to data generated from other distributions. Whether the data was Weibull or generated from other distributions, minimum distance estimation using the Anderson-Darling goodness of fit statitic was the best technique. (Author)

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1986
Accession Number
ADA177581

Entities

People

  • Mark A. Gallagher

Organizations

  • Air Force Institute of Technology

Tags

DTIC Thesaurus Topics

  • Data Science
  • Data Sets
  • Distribution Functions
  • Estimators
  • Information Science
  • Monte Carlo Method
  • Statistical Algorithms
  • Statistical Analysis
  • Statistical Estimation
  • Statistics

Readers

  • Statistical inference.