Search results

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.

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.

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.

The challenge is to determine whether gender discriminates between dead and surviving babies.

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.

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.

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.

Nonparametric ROC analysis using U‐statistics theory was used.

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.

This article will be of value to financial institutions during the process of evaluation/validation of rating models.

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.

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.

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.

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.

This paper supports suggestions in the recent literature to replace pAUC with a new, more meaningful index.

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.

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.

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.

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.

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.

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.

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.

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.

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%.

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.

Curva ROC, Evaluación de riesgos, Riesgo de incumplimiento, Sector bancario, Algoritmo clasificador bayesiano.

Artículo de investigación

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Software defect prediction (SDP) is a critical aspect of software quality assurance, aiming to identify and manage potential defects in software systems. In this paper, we have proposed a novel hybrid approach that combines Gray Wolf Optimization with Feature Selection (GWOFS) and multilayer perceptron (MLP) for SDP. The GWOFS-MLP hybrid model is designed to optimize feature selection, ultimately enhancing the accuracy and efficiency of SDP. Gray Wolf Optimization, inspired by the social hierarchy and hunting behavior of gray wolves, is employed to select a subset of relevant features from an extensive pool of potential predictors. This study investigates the key challenges that traditional SDP approaches encounter and proposes promising solutions to overcome time complexity and the curse of the dimensionality reduction problem.

The integration of GWOFS and MLP results in a robust hybrid model that can adapt to diverse software datasets. This feature selection process harnesses the cooperative hunting behavior of wolves, allowing for the exploration of critical feature combinations. The selected features are then fed into an MLP, a powerful artificial neural network (ANN) known for its capability to learn intricate patterns within software metrics. MLP serves as the predictive engine, utilizing the curated feature set to model and classify software defects accurately.

The performance evaluation of the GWOFS-MLP hybrid model on a real-world software defect dataset demonstrates its effectiveness. The model achieves a remarkable training accuracy of 97.69% and a testing accuracy of 97.99%. Additionally, the receiver operating characteristic area under the curve (ROC-AUC) score of 0.89 highlights the model’s ability to discriminate between defective and defect-free software components.

Experimental implementations using machine learning-based techniques with feature reduction are conducted to validate the proposed solutions. The goal is to enhance SDP’s accuracy, relevance and efficiency, ultimately improving software quality assurance processes. The confusion matrix further illustrates the model’s performance, with only a small number of false positives and false negatives.