Estimating a measure of dependence between two compositions

Research output: Working paper/PreprintWorking paper

75 Downloads (Pure)


We present an estimator of the general measure of correlation for bicompositional data for a sample from a bicompositional Dirichlet distribution. Two confidence intervals are also presented and we examine their empirical confidence coefficient using a Monte Carlo study. Finally we apply the estimator to a data set analysing the correlation between the 1967 and 1997 composition of the government GDP for the 50 U.S. states and District of Columbia.
Original languageEnglish
PublisherDepartment of Statistics, Lund university
Number of pages14
Publication statusPublished - 2010

Subject classification (UKÄ)

  • Probability Theory and Statistics

Free keywords

  • Composition
  • Correlation
  • Dirichlet distribution
  • Empirical confidence coefficient
  • Estimation
  • Joint correlation coefficient


Dive into the research topics of 'Estimating a measure of dependence between two compositions'. Together they form a unique fingerprint.

Cite this