skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Analyzing bioassay data using Bayesian methods -- A primer

Abstract

The classical statistics approach used in health physics for the interpretation of measurements is deficient in that it does not take into account needle in a haystack effects, that is, correct identification of events that are rare in a population. This is often the case in health physics measurements, and the false positive fraction (the fraction of results measuring positive that are actually zero) is often very large using the prescriptions of classical statistics. Bayesian statistics provides a methodology to minimize the number of incorrect decisions (wrong calls): false positives and false negatives. The authors present the basic method and a heuristic discussion. Examples are given using numerically generated and real bioassay data for tritium. Various analytical models are used to fit the prior probability distribution in order to test the sensitivity to choice of model. Parametric studies show that for typical situations involving rare events the normalized Bayesian decision level k{sub {alpha}} = L{sub c}/{sigma}{sub 0}, where {sigma}{sub 0} is the measurement uncertainty for zero true amount, is in the range of 3 to 5 depending on the true positive rate. Four times {sigma}{sub 0} rather than approximately two times {sigma}{sub 0}, as in classical statistics, would seem amore » better choice for the decision level in these situations.« less

Authors:
; ; ; ;
Publication Date:
Research Org.:
Los Alamos National Lab., NM (US)
OSTI Identifier:
20075789
Resource Type:
Journal Article
Journal Name:
Health Physics
Additional Journal Information:
Journal Volume: 78; Journal Issue: 6; Other Information: PBD: Jun 2000; Journal ID: ISSN 0017-9078
Country of Publication:
United States
Language:
English
Subject:
61 RADIATION PROTECTION AND DOSIMETRY; RADIATION DOSES; DATA COVARIANCES; BIOASSAY; DOSIMETRY; STATISTICS; TRITIUM

Citation Formats

Miller, G., Inkret, W.C., Schillaci, M.E., Martz, H.F., and Little, T.T. Analyzing bioassay data using Bayesian methods -- A primer. United States: N. p., 2000. Web. doi:10.1097/00004032-200006000-00002.
Miller, G., Inkret, W.C., Schillaci, M.E., Martz, H.F., & Little, T.T. Analyzing bioassay data using Bayesian methods -- A primer. United States. doi:10.1097/00004032-200006000-00002.
Miller, G., Inkret, W.C., Schillaci, M.E., Martz, H.F., and Little, T.T. Thu . "Analyzing bioassay data using Bayesian methods -- A primer". United States. doi:10.1097/00004032-200006000-00002.
@article{osti_20075789,
title = {Analyzing bioassay data using Bayesian methods -- A primer},
author = {Miller, G. and Inkret, W.C. and Schillaci, M.E. and Martz, H.F. and Little, T.T.},
abstractNote = {The classical statistics approach used in health physics for the interpretation of measurements is deficient in that it does not take into account needle in a haystack effects, that is, correct identification of events that are rare in a population. This is often the case in health physics measurements, and the false positive fraction (the fraction of results measuring positive that are actually zero) is often very large using the prescriptions of classical statistics. Bayesian statistics provides a methodology to minimize the number of incorrect decisions (wrong calls): false positives and false negatives. The authors present the basic method and a heuristic discussion. Examples are given using numerically generated and real bioassay data for tritium. Various analytical models are used to fit the prior probability distribution in order to test the sensitivity to choice of model. Parametric studies show that for typical situations involving rare events the normalized Bayesian decision level k{sub {alpha}} = L{sub c}/{sigma}{sub 0}, where {sigma}{sub 0} is the measurement uncertainty for zero true amount, is in the range of 3 to 5 depending on the true positive rate. Four times {sigma}{sub 0} rather than approximately two times {sigma}{sub 0}, as in classical statistics, would seem a better choice for the decision level in these situations.},
doi = {10.1097/00004032-200006000-00002},
journal = {Health Physics},
issn = {0017-9078},
number = 6,
volume = 78,
place = {United States},
year = {2000},
month = {6}
}