Advanced

A measure of dependence between two compositions

Bergman, Jakob LU and Holmquist, Björn LU (2009)
Abstract
A composition is a vector of positive components summing to a constant.

We consider the problem of describing the correlation between two compo-

sitions. Using a bicompositional Dirichlet distribution, we calculate a joint

correlation coefficient, based on the concept of information gain, between two

compositions. Numerical values of the joint correlation coefficient are calcu-

lated for compositions of two and three components.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Working Paper
publication status
published
subject
keywords
Dirichlet distribution, Correlation, Composition, Binomial coefficient differentiation, Simplex
pages
12 pages
publisher
Department of Statistics, Lund university
language
English
LU publication?
yes
id
554dfb77-d3ca-4c18-aeac-558d9ae64b1b (old id 1580926)
alternative location
http://www.stat.lu.se/publikationer/wp
date added to LUP
2010-03-31 13:21:29
date last changed
2016-04-16 09:36:55
@misc{554dfb77-d3ca-4c18-aeac-558d9ae64b1b,
  abstract     = {A composition is a vector of positive components summing to a constant.<br/><br>
We consider the problem of describing the correlation between two compo-<br/><br>
sitions. Using a bicompositional Dirichlet distribution, we calculate a joint<br/><br>
correlation coefficient, based on the concept of information gain, between two<br/><br>
compositions. Numerical values of the joint correlation coefficient are calcu-<br/><br>
lated for compositions of two and three components.},
  author       = {Bergman, Jakob and Holmquist, Björn},
  keyword      = {Dirichlet distribution,Correlation,Composition,Binomial coefficient differentiation,Simplex},
  language     = {eng},
  pages        = {12},
  publisher    = {ARRAY(0xa64feb0)},
  title        = {A measure of dependence between two compositions},
  year         = {2009},
}