A measure of dependence between two compositions
Author
Summary, in English
We consider the problem of describing the correlation between two compositions. 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 calculated for compositions of two and three components. We also present an estimator of the joint correlation coefficient for a sample from a bicompositional Dirichlet distribution. Two confidence intervals are also presented and we examine their empirical confidence coefficient using Monte Carlo study. Finally we apply the estimator to a data set analysing the correlation between the 1967 and 1997, and the 1977 and 1997 compositions of the government gross domestic product for the 50 U.S. states and District of Columbia.
Department/s
Publishing year
2012
Language
English
Pages
451-461
Publication/Series
Australian & New Zealand Journal of Statistics
Volume
54
Issue
4
Full text
- Available as PDF - 376 kB
- Download statistics
Links
Document type
Journal article
Publisher
Wiley-Blackwell
Topic
- Probability Theory and Statistics
Keywords
- correlation
- Dirichlet distribution
- empirical confidence coefficient
- Fraser information
- joint correlation coefficient
- simplex
Status
Published
ISBN/ISSN/Other
- ISSN: 1467-842X