Asymptotic Expansions of the Distributions of Some Classification Statistics and the Probabilities of Misclassification when the Training Samples are Dependent.

Abstract

Asymptotic expansions of the distributions of some classification statistics and associated probabilities of misclassification are considered for a two population classification problem when the population distributions follow a stationary Gaussian process. Special cases have been considered when the population distributions follow a first order autoregressive process and, in particular, the probabilities of misclassification is studied as a function of the measure of dependence between the two populations. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 22, 1976
Accession Number
ADA035049

Entities

People

  • Shibdas Bandyopadhyay
  • Somesh Das Gupta

Organizations

  • University of Minnesota

Tags

Communities of Interest

  • C4I
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Asymptotic Series
  • Classification
  • Data Science
  • Demography
  • Gaussian Processes
  • Information Science
  • Military Research
  • Minnesota
  • New York
  • Normal Distribution
  • Probability
  • Stationary
  • Statistical Analysis
  • Statistics
  • Training
  • Universities

Fields of Study

  • Mathematics

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Approximation Theory.
  • Wetland-Land-Environmental Management.