Some Limit Theorems for the Indistinguishable Ball Problem with Applications in Nonparametrics.

Abstract

Consider the following urn model, m urns and distribute n indistinguishable balls among the urns such that the distinguishable distributions of the balls all have the same probability. Let S sub K denote the number of balls in the Kth urn. Clearly S sub 1 + ... + S sub m = n. In this paper, random variables of the type Z = h(S sub 1,...,S sub m), especially h(S sub 1, ...,S sub m) = h sub 1 (S sub 1) + ... + h sub m (S sub m), are studied when m,n approaches the limit of infinity m/n approaches the limit of rho, o < rho < infinity. Some applications of the results in nonparametric statistics are briefly discussed and the limit distribution of mas(S sub1,...,S sub m) is derived.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1976
Accession Number
ADA031957

Entities

People

  • Lars Holst

Organizations

  • University of Wisconsin–Madison

Tags

DTIC Thesaurus Topics

  • Computing-Related Activities
  • Contracts
  • Data Science
  • Information Science
  • Interdisciplinary Science
  • Mathematics
  • Military Research
  • New York
  • Nonparametric Statistics
  • North Carolina
  • Numbers
  • Probability
  • Random Variables
  • Real Numbers
  • Statistical Inference
  • Statistics
  • United States

Fields of Study

  • Mathematics

Readers

  • Analytical Mechanics
  • Mathematics or Statistics
  • Statistical inference.