Search results
1 – 10 of 478Maria Filipa Mourão, Ana Cristina Braga and Pedro Nuno Oliveira
The purpose of this paper is to use the kernel method to produce a smoothed receiver operating characteristic (ROC) curve and show how baby gender can influence Clinical…
Abstract
Purpose
The purpose of this paper is to use the kernel method to produce a smoothed receiver operating characteristic (ROC) curve and show how baby gender can influence Clinical Risk Index for Babies (CRIB) scale according to survival risks.
Design/methodology/approach
To obtain the ROC curve, conditioned by covariates, two methods may be followed: first, indirect adjustment, in which the covariate is first modeled within groups and then by generating a modified distribution curve; second, direct smoothing in which covariate effects is modeled within the ROC curve itself. To verify if new-born gender and weight affects the classification according to the CRIB scale, the authors use the direct method. The authors sampled 160 Portuguese babies.
Findings
The smoothing applied to the ROC curves indicates that the curve's original shape does not change when a bandwidth h=0.1 is used. Furthermore, gender seems to be a significant covariate in predicting baby deaths. A higher value was obtained for the area under curve (AUC) when conditional on female babies.
Practical implications
The challenge is to determine whether gender discriminates between dead and surviving babies.
Originality/value
The authors constructed empirical ROC curves for CRIB data and empirical ROC curves conditioned on gender. The authors calculate the corresponding AUC and tested the difference between them. The authors also constructed smooth ROC curves for two approaches.
Details
Keywords
Ana Cristina Braga and Pedro Oliveira
Receiver operating characteristic (ROC) analysis is a powerful tool to measure and specify the problems with diagnostic performance in medicine. Describes this analysis…
Abstract
Receiver operating characteristic (ROC) analysis is a powerful tool to measure and specify the problems with diagnostic performance in medicine. Describes this analysis and the importance of the index area under ROC curve, using some examples to demonstrate its application. The study was conducted on two sets of new‐borns with very low birth weight, coming from neonatal intensive care units from Portuguese hospitals. The first application uses correlated samples, and aims to define which of the five indices of clinical seriousness can be considered the best to evaluate the risk of death for babies with very low birth weight. In the second application, regarding independent samples, compares four Portuguese hospitals, the aim being to identify the neonatal intensive care unit which presents the best performance in terms of care to the new‐borns, i.e. evaluated through the comparison of the clinical severity indices.
Details
Keywords
Stylianos Z. Xanthopoulos and Christos T. Nakas
The purpose of this article is to introduce Receiver Operating Characteristic (ROC) surfaces and hyper‐surfaces within a banking context as natural generalizations of the…
Abstract
Purpose
The purpose of this article is to introduce Receiver Operating Characteristic (ROC) surfaces and hyper‐surfaces within a banking context as natural generalizations of the ROC curve.
Design/methodology/approach
Nonparametric ROC analysis using U‐statistics theory was used.
Findings
Application of the proposed methodology on data from a small size Greek bank illustrates the usefulness of ROC analysis for scoring systems assessment. The area under the ROC curve and the volume under the ROC surface and hyper‐surface are useful diagnostic indices for the assessment of credit rating systems and scorecards. The notion of statistical significance is not adequate for the evaluation of the loan granting strategy of a financial institution.
Originality/value
This article will be of value to financial institutions during the process of evaluation/validation of rating models.
Details
Keywords
Mehmet Tolga Taner, Bulent Sezen and Kamal Atwat
This paper aims to compare two diagnostic performance measures, i.e. signal‐to‐noise ratio (S/N ratio) and partial area under receiver operating characteristic curves…
Abstract
Purpose
This paper aims to compare two diagnostic performance measures, i.e. signal‐to‐noise ratio (S/N ratio) and partial area under receiver operating characteristic curves (pAUC). It proposes the use of S/N ratio rather than pAUC for establishing optimal cut‐off point for diagnostic biomarkers.
Design/methodology/approach
This paper discusses the properties, uses, advantages and shortcomings of the two performance measures, namely the partial area under receiver operating characteristic curve (pAUC) and Taguchi's signal‐to‐noise (S/N) ratio. The benefits of S/N ratio have been illustrated in a sample of four biomarkers, each having five cut‐off points. The S/N ratio is compared to the pAUC index. The SAS software is employed to calculate pAUC and AUC.
Findings
This paper shows that S/N ratio can be used as a measure of diagnostic accuracy. The cut‐off point with the highest S/N ratio is the optimal cut‐off point for the biomarker. The proposed method has the advantages of being easier, more practical and less costly than that of pAUC.
Practical implications
This paper includes implications for the development of a more practical, equally powerful and less costly means of measuring clinical accuracy thereby reducing the costs and risks resulting from wrong selection of cut‐off point can be decreased.
Originality/value
This paper supports suggestions in the recent literature to replace pAUC with a new, more meaningful index.
Details
Keywords
Majid Jaraiedi and Wafik H. Iskander
Signal Detection Theory (SDT) has recently been used to evaluate the performance of imperfect inspectors. SDT model is based on a priori probabilities and perceived…
Abstract
Signal Detection Theory (SDT) has recently been used to evaluate the performance of imperfect inspectors. SDT model is based on a priori probabilities and perceived payoffs and penalties to study inspectors′ behaviour. In this article, Bayes′ theorem is used to compute posterior probabilities of the two types of inspection error. These posterior probabilities give rise to the definition of Receiver Analysis Curves (RAC), which depict the “after the facts” consequences of inspection error. A cost model is also developed that reflects the true benefits and costs of inspection accuracy to the organisation.
Details
Keywords
Diagnostic tests are widely used in many areas of modern technological society, but they are of particular importance in medicine, where early and accurate diagnosis can…
Abstract
Diagnostic tests are widely used in many areas of modern technological society, but they are of particular importance in medicine, where early and accurate diagnosis can decrease morbidity and mortality rates of disease. How the quality of diagnostic information and decisions should be measured in a meaningful way has become increasingly important in recent years as an abundance of new diagnostic tests have been introduced. A number of seemingly independent indices are studied for evaluating diagnostic performance such as the receiver operating characteristic curves and signal‐to‐noise ratios. Designing robustness into diagnostic tests can only be achieved by minimizing the variation in the total number of false diagnosis. This article has undertaken a comparison of signal‐to‐noise ratios developed by Taguchi in quality engineering and system performance in manufacturing industry. A hybrid is also computed and its relevance to physicians as an efficient assessment method is proposed and strongly encouraged.
Details
Keywords
Loan default risk or credit risk evaluation is important to financial institutions which provide loans to businesses and individuals. Loans carry the risk of being…
Abstract
Purpose
Loan default risk or credit risk evaluation is important to financial institutions which provide loans to businesses and individuals. Loans carry the risk of being defaulted. To understand the risk levels of credit users (corporations and individuals), credit providers (bankers) normally collect vast amounts of information on borrowers. Statistical predictive analytic techniques can be used to analyse or to determine the risk levels involved in loans. This paper aims to address the question of default prediction of short-term loans for a Tunisian commercial bank.
Design/methodology/approach
The authors have used a database of 924 files of credits granted to industrial Tunisian companies by a commercial bank in the years 2003, 2004, 2005 and 2006. The naive Bayesian classifier algorithm was used, and the results show that the good classification rate is of the order of 63.85 per cent. The default probability is explained by the variables measuring working capital, leverage, solvency, profitability and cash flow indicators.
Findings
The results of the validation test show that the good classification rate is of the order of 58.66 per cent; nevertheless, the error types I and II remain relatively high at 42.42 and 40.47 per cent, respectively. A receiver operating characteristic curve is plotted to evaluate the performance of the model. The result shows that the area under the curve criterion is of the order of 69 per cent.
Originality/value
The paper highlights the fact that the Tunisian central bank obliged all commercial banks to conduct a survey study to collect qualitative data for better credit notation of the borrowers.
Propósito
El riesgo de incumplimiento de préstamos o la evaluación del riesgo de crédito es importante para las instituciones financieras que otorgan préstamos a empresas e individuos. Existe el riesgo de que el pago de préstamos no se cumpla. Para entender los niveles de riesgo de los usuarios de crédito (corporaciones e individuos), los proveedores de crédito (banqueros) normalmente recogen gran cantidad de información sobre los prestatarios. Las técnicas analíticas predictivas estadísticas pueden utilizarse para analizar o determinar los niveles de riesgo involucrados en los préstamos. En este artículo abordamos la cuestión de la predicción por defecto de los préstamos a corto plazo para un banco comercial tunecino.
Diseño/metodología/enfoque
Utilizamos una base de datos de 924 archivos de créditos concedidos a empresas industriales tunecinas por un banco comercial en 2003, 2004, 2005 y 2006. El algoritmo bayesiano de clasificadores se llevó a cabo y los resultados muestran que la tasa de clasificación buena es del orden del 63.85%. La probabilidad de incumplimiento se explica por las variables que miden el capital de trabajo, el apalancamiento, la solvencia, la rentabilidad y los indicadores de flujo de efectivo.
Hallazgos
Los resultados de la prueba de validación muestran que la buena tasa de clasificación es del orden de 58.66% ; sin embargo, los errores tipo I y II permanecen relativamente altos, siendo de 42.42% y 40.47%, respectivamente. Se traza una curva ROC para evaluar el rendimiento del modelo. El resultado muestra que el criterio de área bajo curva (AUC, por sus siglas en inglés) es del orden del 69%.
Originalidad/valor
El documento destaca el hecho de que el Banco Central tunecino obligó a todas las entidades del sector llevar a cabo un estudio de encuesta para recopilar datos cualitativos para un mejor registro de crédito de los prestatarios.
Palabras clave
Curva ROC, Evaluación de riesgos, Riesgo de incumplimiento, Sector bancario, Algoritmo clasificador bayesiano.
Tipo de artículo
Artículo de investigación
Details
Keywords
Christos Kouimtsidis, Daniel Stahl, Robert West and Colin Drummond
The purpose of this paper is to test the discriminative validity of the Substance Use Beliefs Questionnaire (SUBQ) with alcohol dependent users, by assessing if the new…
Abstract
Purpose
The purpose of this paper is to test the discriminative validity of the Substance Use Beliefs Questionnaire (SUBQ) with alcohol dependent users, by assessing if the new tool can successfully differentiate between two extreme groups.
Design/methodology/approach
The criterion used to select the two extreme groups was participation or not in treatment for alcohol dependence. Score of the Severity of Alcohol Dependence Questionnaire (SADQ) was used as a secondary confirmation criterion of extreme difference.
Findings
In all, 98 staff and 94 people in treatment for alcohol dependence were recruited. The treatment group scored 30.83 higher than the control on SADQ, 10.76 on positive and 28.98 on negative expectancies. Negative expectancies score had correctly classified 88.5 per cent and positive expectancies score only 66 per cent of the original grouped cases. The area under the Receiver Operating Characteristics (ROC) curve for negative expectancies was 0.94 (very good) with a cut-off point of 43.5 with 89 per cent sensitivity and 92 per cent specificity. The area under the ROC curve for positive expectancies was 0.73 (fair). Due to the shape it was difficult to identify a cut-off point.
Research limitations/implications
The results support the discriminative validity of the negative expectancies sub scale of the SUBQ between two extreme groups. With only the use of negative expectancies score participants could be classified correctly to those of the control and those of the treatment group.
Originality/value
SUBQ is the first tool to measure outcome expectancies across substances, facilitating relevant research with poly substance users. Future research needs to explore the discriminative validity of the tool with the other three substance groups (smokers, stimulant and opioids users), involved in the development and validation of the SUBQ.
Details
Keywords
Benjamin P. Foster and Jozef Zurada
Recent bankruptcy research uses hazard models and extensive samples of companies. The large samples used have precluded the inclusion of a variable related to companies'…
Abstract
Purpose
Recent bankruptcy research uses hazard models and extensive samples of companies. The large samples used have precluded the inclusion of a variable related to companies' loan default status in the models. With a sample limited to financially distressed companies, the authors aim to examine if results differ when loan default status and/or audit opinion variables are omitted from hazard bankruptcy prediction models.
Design/methodology/approach
The sampling frame is publicly traded US companies, consisting of 111 bankrupt and 310 matching companies from 2003 to 2007. The study applies logistic regression to choose variables for parsimonious bankruptcy prediction models to validate hypotheses. Loan default status and/or audit opinion variables are included as potential predictive variables along with variables included in previous hazard bankruptcy prediction models.
Findings
Results reveal that loan default and audit opinion variables: improve the predictive accuracy for financially distressed samples with hazard model characteristics; and change the significance on some variables included in previous hazard models.
Research limitations/implications
Auditors' propensity to issue going‐concern modifications varies over time. To allow manual collection of loan default status information, the authors' sample was limited. Consequently, their results may not be generalizable to other bankruptcy hazard models.
Practical implications
Results from hazard models that do not include loan default status or auditor opinion variables should be interpreted with caution. Auditors might improve their going‐concern modification decisions by attributing more importance to loan default status. Also, the auditor's opinion adds incremental bankruptcy risk information to lenders and investors.
Originality/value
Recent bankruptcy research uses hazard models and extensive samples of companies. However, these studies omit a potentially important variable available to financial statement users, loan default status. The authors demonstrate that including variables for loan default status and auditor's opinion improves bankruptcy prediction models and can change conclusions drawn about other variables.
Details
Keywords
Jeffery S McMullen and Dean A Shepherd
Shane and Venkataraman (2000) suggest “the field [of entrepreneurship] involves the study of sources of opportunities; the processes of discovery, evaluation, and…
Abstract
Shane and Venkataraman (2000) suggest “the field [of entrepreneurship] involves the study of sources of opportunities; the processes of discovery, evaluation, and exploitation of opportunities; and the set of individuals who discover, evaluate, and exploit them” (p. 218). However, the study of the judgment required for opportunity evaluation has been greatly overshadowed by interest in opportunity recognition and to a lesser extent opportunity exploitation. This is surprising considering the number of economic theories of the entrepreneur that recognize sound judgment as a principal quality of entrepreneurship (Cantillon, 1755; Kirzner, 1973; Knight, 1921; Mises, 1949; Say, 1840; Schumpeter, 1934; Shackle, 1955). In fact, the first recognized theory of the entrepreneur defined the entrepreneur as someone who exercises business judgment in the face of uncertainty (Cantillon, 1755/1931, pp. 47–49). Similarly, Knight (1921, p. 271) suggests that the essence of entrepreneurship is judgment, born of uncertainty, and argues that it is this judgment that delineates the function of entrepreneur from that of manager. He goes on to point out that the function of manager does not in itself imply entrepreneurship but that a manager becomes an entrepreneur when he exercises judgment involving liability to error (Knight, 1921, p. 97). However, the judgment referred to by these theorists is not just any form of judgment, it is judgment exercised in the decision of whether to take action.