Marialuisa Restaino

Forecasting corporate bankruptcy: empirical evidence on Italian data

Purpose – The aim of the paper is to investigate several aspects of bankruptcy prediction within both theoretical and empirical frameworks. In particular, it has focused on the comparison of different techniques used to forecast failure through a balanced sample of companies within a geographical area (the Campania region) located in the south of Italy.Methodology – Business failure has been one of the most investigated topics within corporate finance and the empirical approach to bankruptcy prediction has recently gained further attention from financial institutions. The aim of corporate failure prediction is to have a methodological approach which discriminates firms with a high probability of future failure from those which are considered to be healthy. Starting from the seminal paper of Altman (1968), many other significant contributions have been subsequently made to this field (Ravi Kumar and Ravi, 2007). This papers approach is to compare different statistical techniques based on the analysis of f...

Predicting risk of 2-year incident dementia using the CAMCOG total and subscale scores

BACKGROUND being able to identify individuals at high risk of dementia is important for diagnostics and intervention. Currently, there is no standard approach to assessing cognitive function in older aged individuals to best predict incident dementia. OBJECTIVE to identify cognitive changes associated with an increased risk of 2-year incident dementia using the Cambridge Cognitive Examination (CAMCOG). DESIGN longitudinal population representative sample aged 65+ years. METHODS individuals were from the Medical Research Council Cognitive Function and Ageing Study. Classification and Regression Tree analysis was used to detect the optimal cut-off value for the CAMCOG total, subscales and composite memory and non-memory scores, for predicting dementia. Sensitivity and specificity of each cut-off score were assessed. RESULTS from the 2,053 individuals without dementia at the first assessment, 137 developed dementia at the 2-year follow-up. The results indicate similar discriminative accuracy for incident dementia based on the CAMCOG total, memory subscale and composite scores. However, sensitivity and specificity of cut-off values were generally moderate. Scores on the non-memory subscales generally had high sensitivity but low specificity. Compared with the CAMCOG total score they had significantly lower discriminative accuracy. CONCLUSION in a population setting, cut-off scores from the CAMCOG memory subscales predicted dementia with reasonable accuracy. Scores on the non-memory scales have lower accuracy and are not recommend for predicting high-risk cases unless all non-memory subdomain scores are combined. The added value of cognition when assessed using the CAMCOG to other risk factors (e.g. health and genetics) should be tested within a risk prediction framework.

Factors associated with urban non-fatal road-accident severity

ABSTRACT This paper reports on the factors associated with non-fatal urban-road accident severity. Data on accidents were gathered from the local traffic police in the City of Palermo, one of the six most populated cities in Italy. Findings from a mixed-effects logistic-regression model suggest that accident severity increases when two young drivers are involved, road traffic conditions are light/normal and when vehicles crash on a two-way road or carriageway. Speeding is more likely to cause slight or serious injury even when compared to a vehicle moving towards the opposite direction of traffic. An accident during the summer is more likely to result in a slight or serious injury than an accident during the winter, which is in line with evidence from Southern Europe and the Middle East. Finally, the severity of non-fatal accident injuries in an urban area of Southern Europe was significantly associated with speeding, the age of the driver and seasonality.

A class of nonparametric bivariate survival function estimators for randomly censored and truncated data

ABSTRACT This paper proposes a class of nonparametric estimators for the bivariate survival function estimation under both random truncation and random censoring. In practice, the pair of random variables under consideration may have certain parametric relationship. The proposed class of nonparametric estimators uses such parametric information via a data transformation approach and thus provides more accurate estimates than existing methods without using such information. The large sample properties of the new class of estimators and a general guidance of how to find a good data transformation are given. The proposed method is also justified via a simulation study and an application on an economic data set.

Variable Selection in Estimating Bank Default

The crisis of the first decade of the 21st century has definitely changed the approaches used to analyze data originated from financial markets. This break and the growing availability of information have lead to revise the methodologies traditionally used to model and evaluate phenomena related to financial institutions. In this context we focus the attention on the estimation of bank defaults: a large literature has been proposed to model the binary dependent variable that characterizes this empirical domain and promising results have been obtained from the application of regression methods based on the extreme value theory. In this context we consider, as dependent variable, a strongly asymmetric binary variable whose probabilistic structure can be related to the Generalized Extreme Value (GEV) distribution. Further we propose to select the independent variables through proper penalty procedures and appropriate data screenings that could be of great interest in presence of large datasets.

Optimal Cut-Off Points for Multiple Causes of Business Failure Models

In studies involving bankruptcy prediction models, since the attention is focused on the classification of firms into groups according to their financial status and the prediction of the status for new firms, optimal cutoff points have to be chosen. Some methods have been developed for two-group classification. Until now, there are few references on how to determine optimal thresholds when the groups are more than two. Here, a method based on the optimization of both correct classification rate and expected cost misclassification (ECM) is proposed for determining optimal cutoff points when there are multiple causes of business failure. The proposed procedure has been tested on a real data set.

An Empirical Comparison of Variable Selection Methods in Competing Risks Model

The variable selection is a challenging task in statistical analysis. In many real situations, a large number of potential predictors are available and a selection among them is recommended. For dealing with this problem, the automated procedures are the most commonly used methods, without taking into account their drawbacks and disadvantages. To overcome them, the shrinkage methods are a good alternative. Our aim is to investigate the performance of some variable selection methods, focusing on a statistical procedure suitable for the competing risks model. In this theoretical setting, the same variables might have different degrees of influence on the risks due to multiple causes and this has to be taken into account in the choice of the “best” subset. The proposed procedure, based on shrinkage techniques, is evaluated by means of empirical analysis on a data-set of financial indicators computed from a sample of industrial firms annual reports.

Detecting Short-Term Cycles in Complex Time Series Databases

Time series characterize a large part of the data stored in financial, medical and scientific databases. The automatic statistical modelling of such data may be a very hard problem when the time series show “complex” features, such as nonlinearity, local nonstationarity, high frequency, long memory and periodic components. In such a context, the aim of this paper is to analyze the problem of detecting automatically the different periodic components in the data, with particular attention to the short term components (weakly, daily and intra-daily cycles). We focus on the analysis of real time series from a large database provided by an Italian electric company. This database shows complex features, either for the high dimension or the structure of the underlying process. A new classification procedure we proposed recently, based on a spectral analysis of the time series, was applied on the data. Here we perform a sensitivity analysis for the main tuning parameters of the procedure. A method for the selection of the optimal partition is then proposed.

Variable selection in forecasting models for default risk

The aim of the paper is to investigate different aspects involved in developing prediction models in default risk analysis. In particular, we focused on the comparison of different statistical methods addressing several issues such as the structure of the data-base, the sampling procedure and the selection of financial predictors by means of different variable selection techniques. The analysis is carried out on a data-set of accounting ratios created from a sample of industrial firms annual reports. The reached findings aim to contribute to the elaboration of efficient prevention and recovery strategies.