Robust Permutation Tests for Homogeneity of Fingerprint Patterns of Dioxin Congener Profiles

• Activity Number: 84
• Type: Contributed
• Date/Time: Sunday, July 29, 2012 : 4:00 PM to 5:50 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Chu-Chih Chen*+ and Pranab K. Sen
• Companies: National Health Research Institutes and The University of North Carolina at Chapel Hill
• Keywords: aligned ranks ; arithmetic mean ; compositional data ; Dirichlet distribution ; geometric mean ; logistic normal distribution

Abstract

Fingerprint analysis comparing the polychlorinated dibenzo-p-dioxin and dibenzofuran (PCDD/F) congener profile patterns of collected samples with those of potential dioxin emission source(s) is an important tool for identifying environmental dioxin pollutions. The constraint that the proportions of the seventeen PCDD/F congeners comprising a fingerprint sum up to one motivates a multivariate gamma distribution, which leads to a Dirichlet distribution. Because of the complexity in restricted likelihood ratio tests (LRT) and typical sample size limitations resulting from laboratory analysis costs, permutation test procedures are employed for hypothesis testing of the homogeneity of congener profiles. Pearson-type chi-squared tests based on the Dirichlet distribution (DM) assumption, the generalized form of DM using the arithmetic mean (AM) and geometric mean (GM) of the proportions, and the robust aligned rank (AR) test, are proposed and compared through simulations. PCDD/F samples collected from the stack of a local municipal solid waste incinerator (MSWI) and from ambient air near the MSWI in Taiwan were illustrated as an example. The simulation results showed that the AR test, fol