An environmental sampling model for combining judgmental and randomly placed samples.
Sego-LH; Bennett-J; Anderson-KK; Gillen-M; Matzke-BD; Wilson-JE; Sieber-K; Pulsipher-BA; Shulman-S
Washington, DC: U.S. Department of Energy, 2007 Aug; :1-19
In the event of the release of a lethal agent (i.e. Bacillus anthracis) inside a building, law enforcement and public health responders take samples to identify and characterize the contamination. Sample locations may be rapidly chosen based on available incident details and professional judgment. To achieve greater confidence of whether or not the decision area was contaminated, or to certify that detectable contamination is not present after decontamination, we developed a Bayesian model for combining the information gained from both judgmental and randomly placed samples. The approach permits investigators to determine the sample size required to achieve a defined level of statistical confidence that a decision area is free of detectable contamination, when none of the samples indicate the presence of contamination. We present herein the model, an example of how it may be used, a discussion of its sensitivity to parameter inputs, and recommendations for its practical use.
Bacteria; Sampling; Lethal-concentrations; Infectious-diseases; Carbuncles; Biological-warfare-agents; Biological-weapons; Sampling-methods; Statistical-analysis; Models; Microorganisms; Surveillance-programs;
Author Keywords: Environmental sampling; Judgment sampling; Acceptance sampling; Bayesian modeling; Anthrax; Bioterrorism
Book or book chapter
DART; DSHEFS; OD
An environmental sampling model for combining judgmental and randomly placed samples
Pacific Northwest National Laboratory