Edward Boone

Department of Statistical Sciences and Operations Research, Virginia Commonwealth University, USA

Toxicologists are often interested in determining which dosage of some chemical or stressor will produce an adverse reaction to some outcome or endpoint.  Traditional methods include LOAEL, NOAEL and benchmark dosage approaches.  However, these methods are typically used in a single stressor single endpoint frameworks.  This talk presents a Bayesian method for simultaneously estimating benchmark dosages with multiple endpoints and multiple stressors.  The method is illustrated using both a simulated dataset and real data concerning organophosphorous pesticides on rats.

Ed is an Assistant Professor in the Department of Statistical Sciences and Operations Research at Virginia Commonwealth University. He earned his PhD in Statistics from Virginia Polytechnic Institute and State University (Virginia Tech) in 2003. He primarily works on Bayesian methodology with applications to the Environment and Ecology. He has also worked on projects concerning image recognition and detection of quantitative trait loci.

For information about the speaker, see http://www.stat.vcu.edu/facultyandstaff.htm