Some Case Studies of Skewed (and Other Ab-Normal) Data Distributions Arising in Low-Level Environmental Research

Published

July 1, 2001

Author(s)

Lloyd A. Currie

Abstract

Three general classes of skewed data distributions have been encountered in our research on background radiation, chemical and radiochemical blanks, and low levels of 85Kr and 14C in the atmosphere and the cryosphere. The first skewed data class may be considered to be theoretically, or fundamentally skewed. It is typified by the exponential distribution of inter-arrival times for nuclear counting events for a Poisson process. As part of a study of the nature of low-level (anticoincidence) Geiger-M ller counter background radiation, tests were performed on the Poisson distribution of counts, the uniform distribution of arrival times, and the exponential distribution of inter-arrival times. The real laboratory system, of course, failed the (inter-arrival time) test -- for very interesting reasons, linked to the physics of the measurement process. The second, computationallyskewed class relates to skewness induced by non-linear transformations. It is illustrated by non-linear concentration estimates from inverse calibration, and bivariate blank corrections for low-level 14C-12C aerosol data that led to highly asymmetric uncertainty intervals for the biomass carbon contribution to urban soot.The third, environmentally skewed data class relates to a universal problem for the detection of excursions above blank or baseline levels: namely, the widespread occurrence of ab-normal distributions of environmental and laboratory blanks. This is illustrated by the search for fundamental factors that lurk behind skewed frequency distributions of sulfur laboratory blanks and 85Kr environmental baselines, and the application of robust statistical procedures for reliable detection decisions in the face of skewed isotopic carbon procedural blanks having few degrees of freedom.

Citation

Fresenius Journal of Analytical Chemistry

Volume

370

Issue

No. 6

Pub Type

Journals

Keywords

computationally skewed distributions, detection decision levels, environmentally skewed distributions, exploratory data analysis, fundamentally skewed distributions, isotopic blank corrections, non-linear transformations, Poisson process, skewed data distributions

Citation

Currie, L. (2001), Some Case Studies of Skewed (and Other Ab-Normal) Data Distributions Arising in Low-Level Environmental Research, Fresenius Journal of Analytical Chemistry (Accessed November 8, 2024)