Thesis (M.S.) -- Worcester Polytechnic Institute. / Keywords: Credit risk; Credit default swaps. Includes bibliographical references (leaf 32).

This thesis is concerned with statistical aspects of credit scoring, the process of determining how likely an applicant for credit is to default with repayments. In Chapters 1-4 a detailed introduction to credit scoring methodology is presented, including evaluation of previous published work on credit scoring and a review of discrimination and classification techniques. In Chapter 5 we describe different approaches to measuring the absolute and relative performance of credit scoring models. Two significance tests are proposed for comparing the bad rate amongst the accepts (or the error rate) from two classifiers. In Chapter 6 we consider different approaches to reject inference, the procedure of allocating class membership probabilities to the rejects. One reason for needing reject inference is to reduce the sample selection bias that results from using a sample consisting only of accepted applicants to build new scorecards. We show that the characteristic vectors for the rejects do not contain information about the parameters of the observed data likelihood, unless extra information or assumptions are included. Methods of reject inference which incorporate additional information are proposed. In Chapter 7 we make comparisons of a range of different parametric and nonparametric classification techniques for credit scoring: linear regression, logistic regression, projection pursuit regression, Poisson regression, decision trees and decision graphs. We conclude that classifier performance is fairly insensitive to the particular technique adopted. In Chapter 8 we describe the application of the k-NN method to credit scoring. We propose using an adjusted version of the Eucidean distance metric, which is designed to incorporate knowledge of class separation contained in the data. We evaluate properties of the k-NN classifier through empirical studies and make comparisons with existing techniques.

Risk assessment is essential to ensure safety in hospitals. However, hospitals have paid little attention to risk assessment. Several problems have already been identified in the literature about current risk assessment practice, such as inadequate risk assessment guidance and bias in risk scoring. This research aimed to improve current risk assessment practice in hospitals in the National Health Service (NHS) in England. To address this aim, the research investigated current risk assessment practice and designed a new risk assessment approach by the use of mixed methods. One hundred hospitals’ risk assessment documents were reviewed to examine the current recommended risk assessment practice. Seventeen interviews and sixty-one questionnaires were conducted, a risk management system from a single hospital was reviewed, and strategic risks from thirty-four hospitals were reviewed, in order to examine how risks are assessed in actual practice. Following that, the proposed approach was designed by conducting requirements analysis and then evaluated by interviews and questionnaires with ten healthcare staff. The findings of this research reveal that hospitals conduct risk assessments in different ways (i.e. with a focus on individual patient-based, operational and strategic risks). There are also many problems involved in current risk assessment practice regarding both the foundations and use of risk assessment. For example, organisation-wide risk assessments predominantly rely on risk matrices which might lead to wrong risk prioritisation and resource allocation; and risks tend to reflect existing or past problems rather than being proactive. All these reveal a need to improve current risk assessment practice. This research makes an important contribution to the current understanding of risk assessment practice in hospitals by providing extensive evidence on both recommended and actual practice, and proposes a new risk assessment framework. The framework guides healthcare staff on how to conduct risk assessment in a more comprehensive way by encouraging its potential users to consider good risk assessment practice.

Biotechnology as an industry has come to the fore in the last 2 decades. It is a fast developing industry that offers significant growth opportunities to financial investors with significant advances also being made in terms of the medical fields (blood disorders), agriculture (pest resistant plants), food (genetically modified food) and forensics (DNA fingerprinting). / Prof. A.L. Boessenkool

M.Comm. / ffntroduction Measuring and evaluating risks are essential in a dynamic derivative market to minimize risks. The management of risks in the derivative market is complex due to the non-linear properties of option pricing Method of study The a first step of the study analyzed the "greek" derivatives of a single option contract (e.g. delta, gamma, vega, theta). The next step was to combine and analyze the derivatives of various option contracts. The study pointed out that the risk profile can be amended by combining option contracts. A risk measurement and evaluation model was constructed by creating a table that will simulate option prices at different time horizons and at different market prices. The model will also simulate all the derivatives of options in a table form at different time horizons and at different market prices. The model finally used the tables to reflect the results graphically. Findings The last section of the study was devoted to scenario simulation to identify risks. Firstly the management of the delta was analyzed, and the use of the gamma to identify delta sensitivity was illustrated. The management of the vega was addressed next. The study showed that a combination of options can minimize the risk of vega. The effect of theta or the time value of a option was illustrated and linked to both gamma and vega. The study demonstrated that the results of volatile movements in the market can be simulated by combining the derivatives of options (e.g. add the deltas of options together), and to stress test the strategy. "What if' scenarios can be simulated to illustrate the effect on a current position combined with some amendments.

In this dissertation, we examine current models used to value default-risky bonds. These models include both the structural and the reduced-form approaches. We begin by examining various issues involved in modelling credit risk and pricing credit derivatives. We then explore the various dimensions of structural models and reduced-form models and we provide an overview of four models presented in the literature on credit risk modelling. Both the theoretical and empirical research on default-risky bond valuation is summarized. Finally, we make suggestions for improving on the credit risk models discussed. / Dissertation (MSc (Mathematics of Finance))--University of Pretoria, 2006. / Mathematics and Applied Mathematics / unrestricted

Sampling in onarm production environments presents challenges that must be considered when doing hazard analysis. The sensitivity and specificity of the test used and the sample types chosen will have an impact on the food safety outcome and food safety decisions made during the interpretation of results. In this work, broiler houses were sampled for the presence of Salmonella spp. using two different sampling strategies and four different microbiological isolation procedures. The study was undertaken after complications arose during a field study evaluating the role darkling beetles play in the transmission of foodborne pathogens. It was determined that, based on this work, incorporating a secondary enrichment procedure into the isolation protocol significantly increased the isolation rate from the various sample types, including drag swabs and litter samples. It was also determined that when attempting to characterize the Salmonella-status of a particular broiler house, no one sampling strategy is superior. The results of this study demonstrate that both drag swabs and litter samples need to be utilized to accurately determine if the pathogen is present in a flock. Not only did the secondary enrichment procedure have a higher isolation frequency than the other three methods compared, it also highlighted the discrepancies of the other methods. Two commonly used isolation procedures, tetrathionate and Rappaport-Vassiliadis, were found to disagree on a significant number of samples analyzed. While the isolation frequencies for these procedures were not found to be statistically different, the analysis for agreement, kappa, did indicate that the procedures did not identify the same samples as positive. Overall, the secondary enrichment procedure identified all the samples positive that were also found to be positive by either of the other methods used. Since the secondary enrichment method is a modified version of the traditional delayed secondary enrichment procedure, which requires five additional day of incubation, this study also compared these two procedures. It was determined that the secondary enrichment protocol was as effective for isolating Salmonella from broiler house samples as the delayed secondary enrichment procedure. The secondary enrichment procedure, did however, provide for a quicker turn around for results.

No description available.

No

No