Sensitivity Analysis of Model Output with Input Constraints: A Generalized Rationale for Local Methods

In this work, we introduce a generalized rationale for local sensitivity analysis (SA) methods that allows to solve the problems connected with input constraints. Several models in use in the risk analysis field are characterized by the presence of deterministic relationships among the input parameters. However, SA issues related to the presence of constraints have been mainly dealt with in a heuristic fashion. We start with a systematic analysis of the effects of constraints. The findings can be summarized in the following three effects. (i) Constraints make it impossible to vary one parameter while keeping all others fixed. (ii) The model output becomes insensitive to a parameter if a constraint is solved for that parameter. (iii) Sensitivity analysis results depend on which parameter is selected as dependent. The explanation of these effects is found by proposing a result that leads to a natural extension of the local SA rationale introduced in Helton (1993) . We then extend the definitions of the Birnbaum, criticality, and the differential importance measures to the constrained case. In addition, a procedure is introduced that allows to obtain constrained sensitivity results at the same cost as in the absence of constraints. The application to a nonbinary event tree concludes the article, providing a numerical illustration of the above findings.     

Expert Judgment-Based Risk Assessment Using Statistical Scenario Analysis: A Case Study—Running the Bulls in Pamplona (Spain)

In this article, we present a methodology to assess the risk incurred by a participant in an activity involving danger of injury. The lack of high-quality historical data for the case considered prevented us from constructing a sufficiently detailed statistical model. It was therefore decided to generate a risk assessment model based on expert judgment. The methodology is illustrated in a real case context: the assessment of risk to participants in a San Fermin bull-run in Pamplona (Spain). The members of the panel of "experts on the bull-run" represented very different perspectives on the phenomenon: runners, surgeons and other health care personnel, journalists, civil defense workers, security staff, organizers, herdsmen, authors of books on the bull-run, etc. We consulted 55 experts. Our methodology includes the design of a survey instrument to elicit the experts' views and the statistical and mathematical procedures used to aggregate their subjective opinions.     

企业如何建立科学的信用管理机制

信用销售是市场竞争的结果,加强信用管理是企业当务之急.企业必须建立科学的信用管理机制,成立信用管理部门,规范赊销行为,控制赊销风险.     

Runaway Reactions, Their Courses, and the Methods to Establish Safe Process Conditions

The purpose of this paper is to describe the various process deviations which can cause a runaway reaction to occur, and to discuss the experimental information necessary for risk assessment, the choice of a safe process, and the mitigation of the consequences of the runaway reaction. Ten typical hazardous process situations have been identified, considering various modes of initiation, homogeneous and heterogeneous, Arrhenius, and autocatalytic reactions. Each possible hazardous process deviation is illustrated by examples from the process industry and/or relevant experimental information obtained from laboratory experiments.     

Assessing Cross-Media Impacts: A Comparative Risk Approach

The Oregon Department of Environmental Quality has developed a Cross-Media Comparative Risk Assessment model to address certain regulatory concerns. The model generates a Human and Ecological Risk Index for a facility releasing toxins into the environment. The risk indices are based on chemical fate and transport predictions, toxicity, population density, and ecological sensitive areas. The model can be used to rank facilities for inspection or as a tool to assess the progress of pollution prevention programs. Regulatory permitting departments can use the model to address the cross-media transfer of pollutants from one environmental compartment to another. The versatility of the model allows adaptation to each specific users needs.     

Ethics, Decision Analysis, and Public Risk

In any analysis of a decision problem involving public risks, ethical implications are introduced. In some cases, these ethical implications may be introduced simply because an analysis is being done. Additional ethical implications may be inherently part of the methodology being utilized or introduced into the specific analysis of the decision problem. In this paper, we investigate where and how ethical implications enter when using the methodology of decision analysis to examine problems involving public risks. We conclude that the methodology of decision analysis is sufficiently robust to allow for numerous different ethical viewpoints to be accounted for in any specific analysis. Stated alternatively, decision analyses of public risks can be conducted in a manner consistent with utilitarianism, deontological theories, libertarianism, egalitarianism, and so forth. However, any specific analysis has embedded within it numerous ethical implications. This suggests that the careful ethical scrutiny of analyses involving the methodology of decision analysis should be placed on the specific application and not on the methodology per se or on the fact that an analysis is undertaken.     

Benefit Analysis for Natural Hazards

The objective of this paper is to develop the ex ante perspective for benefit analysis with natural hazards. It defines an ex ante evaluation of the economic benefits that arise from policies designed to reduce either the risk of or the detrimental effects associated with a natural hazard. In the process the paper compares the ex ante and ex post perspectives and discusses the prospects for implementing the framework by measuring the valuation concepts that are developed.     

ESTIMATING THE COMMON MEAN OF A BIVARIATE NORMAL POPULATION

For estimating the common mean of a bivariate normal distribution, Krishnamoorthy & Rohatgi (1989) proposed some estimators which dominate the maximum likelihood estimator in a large region of the parameter space. We consider some modifications of these estimators and study their risk performance.     

The Role of Insurance in Managing Natural Hazard Risks: Private Versus Social Decisions

We explore the interaction between individual and collective decisions concerning natural hazards. Collective actions such as building a dam change the risks faced by private individuals. We show that, with proper incentives, individual reactions to such changes in risk can serve to enhance risk management by utilizing individual's decisions to take account of their specialized knowledge about their risk preferences and losses. We demonstrate that the efficient response to construction of a dam may be private actions that lead to a fully anticipated increase in flood damage. In such instances, zoning that focuses on reducing flood damage may lead to less efficient use of the flood plain. More generally, even where incentives for underinvestment in market insurance and self-insurance are present, constraining use of the flood plain by zoning will not generally lead to efficient outcomes. The model identifying conditions under which informed individuals have the incentives to make efficient decisions is powerful and directs attention toward more fruitful approaches.