On Loss Distributions from Installment-Repaid Loans

The banks have been accumulating huge data bases for many years and are increasingly turning to statistics to provide insight into customer behaviour, among other things. Credit risk is an important issue and certain stochastic models have been developed in recent years to describe and predict loan default. Two of the major models currently used in the industry are considered here, and various ways of extending their application to the case where a loan is repaid in installments are explored. The aspect of interest is the probability distribution of the total loss due to repayment default at some time. Thus, the loss distribution is determined by the distribution of times to default, here regarded as a discrete-time survival distribution. In particular, the probabilities of large losses are to be assessed for insurance purposes.     

A New Look at the Psychometric Paradigm of Perception of Hazards

The psychometric paradigm has been the most influential model in the field of risk analysis. The "cognitive maps" of hazards produced by the paradigm seem to explain how laypeople perceive the various risks they face. Because most of the studies used aggregated data, analyzed using principal component analysis, it is not known whether the model neglects individual differences in risk perception. There has been much criticism on the fact that few studies have examined individual differences in the cognitive representation of hazards. In order to detect and describe the internal structure of the three-way data, we conducted a three-way component analysis (3MPCA). Data for the present analysis were derived from a mail survey conducted in Switzerland. Participants were asked to judge 9 attributes for 26 hazards. Individual differences in the cognitive representation of hazards were correlated with external variables (e.g., general trust). The results suggest that methods permitting individual differences should be used more frequently and that utilizing different methods could provide greater insight into the cognitive representation of risks.     

The 1991 Cholera Epidemic in Peru: Not a Case of Precaution Gone Awry

The precautionary principle calls on decisionmakers to take preventive action in light of evidence indicating that there is a potential for harm to public health and the environment, even though the nature and magnitude of harm are not fully understood scientifically. Critics of the precautionary principle frequently argue that unbridled application of the principle leads to unintended damage to health and ecosystems (risk tradeoffs) and that precautious decision making leaves us vulnerable to "false-positive" risks that divert resources away from "real risks." The 1991 cholera epidemic in Peru is often cited as an example of these pitfalls of the precautionary principle. It has been mistakenly argued that application of the precautionary principle caused decisionmakers to stop chlorinating the water supply due to the risks of disinfection byproducts (DBPs), resulting in the epidemic. Through analyses of investigations conducted in the cities of Iquitos and Trujillo, Peru, literature review, and interviews with leading Peruvian infectious disease researchers, we determined that the epidemic was caused by a much more complex set of circumstances, including poor sanitation conditions, poor separation of water and waste streams, and inadequate water treatment and distribution systems. The evidence indicates that no decision was made to stop chlorinating on the basis of DBP concerns and that concerns raised about DBPs masked more important factors limiting expansion of chlorination. In fact, outside of Peru's capital Lima, chlorination of drinking water supplies at the time of the epidemic was limited at best. We conclude that the Peruvian cholera epidemic was not caused by a failure of precaution but rather by an inadequate public health infrastructure unable to control a known risk: that of microbial contamination of water supplies.     

Using Bayesian Networks to Model Expected and Unexpected Operational Losses

This report describes the use of Bayesian networks (BNs) to model statistical loss distributions in financial operational risk scenarios. Its focus is on modeling "long" tail, or unexpected, loss events using mixtures of appropriate loss frequency and severity distributions where these mixtures are conditioned on causal variables that model the capability or effectiveness of the underlying controls process. The use of causal modeling is discussed from the perspective of exploiting local expertise about process reliability and formally connecting this knowledge to actual or hypothetical statistical phenomena resulting from the process. This brings the benefit of supplementing sparse data with expert judgment and transforming qualitative knowledge about the process into quantitative predictions. We conclude that BNs can help combine qualitative data from experts and quantitative data from historical loss databases in a principled way and as such they go some way in meeting the requirements of the draft Basel II Accord (Basel, 2004) for an advanced measurement approach (AMA).     

非同类企业竞争与合作策略收益模型及风险分析

在比较同类企业竞争策略模型与合作策略模型的基础上,讨论了价格的信息作用,分析了合作策略收益更大和风险并不随之增加的原因。然后以现代决策理念为出发点,探讨了企业最大利润与企业条件的关系,提出了与企业单位变动成本和生产能力条件相适应的合理最大利润的概念,对“理性企业的假设”赋予了“追求与企业条件相适应的合理最大利润”的新含义。据此设计了非同类企业产量分配函数,建立了适用性更广的非同类企业合作策略最佳收益模型,并给出了随市场价格变化的企业最佳应对策略。最后用1个算例来直观体现合作策略的优势。     

An Empirical Investigation of the Assumptions of Risk-Value Models

Do participants make decisions consistent with risk-value tradeoffs? One hundred and five undergraduate business students made risk and preference judgments about lottery pairs in a series of paper surveys. The data indicate that the participants’ responses were generally consistent with the key assumptions of risk-value models, but that some extensions of the theory would improve this consistency. In particular, we find that modifying the risk assumptions of the risk-value theory so they are consistent the concept of the reflection of the risk attitude in the domains of gains and losses increases the agreement between the theory and the participants’ responses.     

Structural Analyses Of The Quality Of Life Of Children At Risk

Quality of life (QOL) is usually assessed in terms of levels. This paper, in contrast, examines the structure of the quality of life of its subjects: two groups of children at risk, children who were kept at home and those who were removed from home. The social workers who made the decisions were asked to assess the children’s quality of life using Shye’s Systemic Quality of Life Model. The study’s main finding is that the QOL structure of the two groups of children differs both from the theoretical “ideal” (or “healthy” structure) and from each other. The QOL structure of the children who were kept at home was closer to the ideal than that of the children who were removed. The difference from the ideal in both groups is consistent with the fact that both groups of children at risk, whose QOL is compromised by definition. The greater proximity to the “ideal” of the QOL structure of the children who were kept at home suggests that the social workers who made the decisions viewed these children as having a healthier QOL than the children who were removed from home.     

Risk Assessment for Carcinogens Under California''s Proposition 65

Risk assessments for carcinogens are being developed through an accelerated process in California as a part of the state's implementation of Proposition 65, the Safe Drinking Water and Toxic Enforcement Act. Estimates of carcinogenic potency made by the California Department of Health Services (CDHS) are generally similar to estimates made by the U.S. Environmental Protection Agency (EPA). The largest differences are due to EPA's use of the maximum likelihood estimate instead of CDHS' use of the upper 95% confidence bounds on potencies derived from human data and to procedures used to correct for studies of short duration or with early mortality. Numerical limits derived from these potency estimates constitute "no significant risk" levels, which govern exemption from Proposition 65's discharge prohibition and warning requirements. Under Proposition 65 regulations, lifetime cancer risks less than 10(-5) are not significant and cumulative intake is not considered. Following these regulations, numerical limits for a number of Proposition 65 carcinogens that are applicable to the control of toxic discharges are less stringent than limits under existing federal water pollution control laws. Thus, existing federal limits will become the Proposition 65 levels for discharge. Chemicals currently not covered by federal and state controls will eventually be subject to discharge limitations under Proposition 65. "No significant risk" levels (expressed in terms of daily intake of carcinogens) also trigger warning requirements under Proposition 65 that are more extensive than existing state or federal requirements. A variety of chemical exposures from multiple sources are identified that exceed Proposition 65's "no significant risk" levels.     

Expert Scientific Judgment and Cancer Risk Assessment: A Pilot Study of Pharmacokinetic Data

When high-dose tumor data are extrapolated to low doses, it is typically assumed that the dose of a carcinogen delivered to target cells is proportional to the dose administered to test animals, even at exposure levels below the experimental range. Since pharmacokinetic data are becoming available that in some cases question the validity of this assumption, risk assessors must decide whether to maintain the standard assumption. A pilot study of formaldehyde is reported that was undertaken to demonstrate how expert scientific judgment can help guide a controversial risk assessment where pharmacokinetic data are considered inconclusive. Eight experts on pharmacokinetic data were selected by a formal procedure, and each was interviewed personally using a structured interview protocol. The results suggest that expert scientific opinion is polarized in this case, a situation that risk assessors can respond to with a range of risk characterizations considered biologically plausible by the experts. Convergence of expert opinion is likely in this case of several specific research strategies ar executed in a competent fashion. Elicitation of expert scientific judgment is a promising vehicle for evaluating the quality of pharmacokinetic data, expressing uncertainty in risk assessment, and fashioning a research agenda that offers possible forging of scientific consensus.     

Risk Prevention and Policy-Making in Automatic Systems

Accidents with automatic production systems are reported to be on the order of one in a hundred or thousand robot-years, while fatal accidents are found to occur one or two orders of magnitude less frequently. Traditions in occupational safety tend to seek for safety targets in terms of zero severe accidents for automatic systems. Decision-making requires a risk assessment balancing potential risk reduction measures and costs within the cultural environment of a production company. This paper presents a simplified procedure which acts as a decision tool. The procedure is based on a risk concept approaching prevention both in a deterministic and in a probabilistic manner. Eight accident scenarios are shown to represent the potential accident processes involving robot interactions with people. Seven prevention policies are shown to cover the accident scenarios in principle. An additional probabilistic approach may indicate which extra safety measures can be taken against what risk reduction and additional costs. The risk evaluation process aims at achieving a quantitative acceptable risk level. For that purpose, three risk evaluation methods are discussed with respect to reaching broad consensus on the safety targets.