Publication detail

Statistical Properties of Discrete Probability Distributions with Maximum Entropy

KARPÍŠEK, Z.

Original Title

Statistical Properties of Discrete Probability Distributions with Maximum Entropy

Type

conference paper

Language

English

Original Abstract

The paper is concerned with the solution of and statistical problem of finding discrete probability distributions conforming to the requirement of maximum entropy under conditions given by estimates of their general moments from the observed relative frequencies. It is shown that the distributions derived are of an exponential type with maximum likelihood estimations of parameters that are also estimations by and modified chi-squared method. Basic properties of these estimations are described and the results are illustrated by examples.

Keywords

maximum entropy, moment conditions, maximum likelihood estimate

Authors

KARPÍŠEK, Z.

RIV year

2001

Released

1. 1. 2001

Publisher

Masaryk University Brno

Location

Masaryk University, Brno

ISBN

80-210-2544-1

Book

Folia Facultatis Scientiarium Naturalium Univesitatis Masarykinae Brunensis

Edition

Mathematica 9. Summer School DATASTAT 99. Proceedings

Edition number

1

Pages from

21

Pages to

32

Pages count

12

BibTex

@inproceedings{BUT3837,
  author="Zdeněk {Karpíšek}",
  title="Statistical Properties of Discrete Probability Distributions with Maximum Entropy",
  booktitle="Folia Facultatis Scientiarium Naturalium Univesitatis Masarykinae Brunensis",
  year="2001",
  series="Mathematica 9. Summer School DATASTAT 99. Proceedings",
  number="1",
  pages="12",
  publisher="Masaryk University Brno",
  address="Masaryk University, Brno",
  isbn="80-210-2544-1"
}