Dependence in Probabilistic Modeling, Dempster-Shafer Theory, and Probability Bounds Analysis; Sandia Report, SAND2004-3072

153, [3] pages. Illustrations. Symbols. Glossary. References. Cover has some wear, soiling, and corner stain to cover and some pages. Scott Ferson is Chair of Uncertainty at the University of Liverpool, School of Engineering, in the Institute for Risk and Uncertainty. He was for many years previously senior scientist at Applied Biomathematics, a research firm on Long Island in New York. He holds a Ph.D. in ecology and evolution from Stony Brook University and an A.B. in biology from Wabash College. He has over 100 peer-reviewed papers and 5 books on risk analysis and related topics. For over twenty years, he has directed methodological research in risk and uncertainty analysis. His recent research work, funded primarily by NIH, NASA and Sandia National Laboratories, has focused on developing methods and software to solve quantitative assessment problems when data are poor or lacking and structural knowledge about the model is severely limited. He has served on many expert panels called by government agencies in the United States and elsewhere. This report summarized methods used to incorporate information about inter-variable dependence into risk assessments that use Dempster-Shafer theory or probability bounds analysis to address epistemic and aleatory uncertainty. The report reviews techniques for simulating correlated variates for a given correlation measure and dependence model, computation of bounds on distribution functions under a specified dependence model, formulation of parametric and empirical dependence models, and bounding approaches that can be used when information about the inter-variable dependence is incomplete. The report also reviews several o f the most pervasive and dangerous myths among risk analysts about dependence in probabilistic models.The Sandia National Laboratories (SNL), managed and operated by the National Technology and Engineering Solutions of Sandia (a wholly owned subsidiary of Honeywell International), is one of three National Nuclear Security Administration research and development laboratories. In December 2016, it was announced that National Technology and Engineering Solutions of Sandia, under the direction of Honeywell International, will take over the management of Sandia National Laboratories starting on May 1, 2017. Their primary mission is to develop, engineer, and test the non-nuclear components of nuclear weapons. The primary campus is located on Kirtland Air Force Base in Albuquerque, New Mexico and the other is in Livermore, California, next to Lawrence Livermore National Laboratory. It is Sandia's mission to maintain the reliability and surety of nuclear weapon systems, conduct research and development in arms control and nonproliferation technologies, and investigate methods for the disposal of the United States' nuclear weapons program's hazardous waste. Other missions include research and development in energy and environmental programs, as well as the surety of critical national infrastructures. In addition, Sandia is home to a wide variety of research including computational biology, mathematics (through its Computer Science Research Institute), materials science, alternative energy, psychology, MEMS, and cognitive science initiatives. Sandia formerly hosted ASCI Red, one of the world's fastest supercomputers until its recent decommission, and now hosts ASCI Red Storm, originally known as Thor's Hammer. Sandia is also home to the Z Machine. The Z Machine is the largest X-ray generator in the world and is designed to test materials in conditions of extreme temperature and pressure. It is operated by Sandia National Laboratories to gather data to aid in computer modeling of nuclear weapons.…