Generalized Extreme Value Regression for Binary Rare Events Data: an Application to Credit Defaults

The most used regression model with binary dependent variable is the logistic regression model. When the dependent variable represents a rare event, the logistic regression model shows relevant drawbacks. In order to overcome these drawbacks we propose the Generalized Extreme Value (GEV) regression model. In particular, in a Generalized Linear Model (GLM) with binary dependent variable we suggest the quantile function of the GEV distribution as link function, so our attention is focused on the tail of the response curve for values close to one. The estimation procedure is the maximum likelihood method. This model accommodates skewness and it presents a generalization of GLMs with log-log link function. In credit risk analysis a pivotal topic is the default probability estimation. Since defaults are rare events, we apply the GEV regression to empirical data on Italian Small and Medium Enterprises (SMEs) to model their default probabilities.

[1]  Alex W. H. Chan.  Merton, Robert C. , 2010 .

[2]  David J. Hand,et al.  Statistical Classification Methods in Consumer Credit Scoring: a Review , 1997 .

[3]  E. Altman,et al.  Modeling Credit Risk for Smes: Evidence from the Us Market , 2005 .

[4]  A. McNeil.  Extreme Value Theory for Risk Managers , 1999 .

[5]  Annette J. Dobson,et al.  An introduction to generalized linear models , 1991 .

[6]  Eric R. Ziegel,et al.  An Introduction to Generalized Linear Models , 2002, Technometrics.

[7]  S. Nadarajah,et al.  Extreme value distributions , 2013 .

[8]  Jesús Saurina,et al.  The Impact of Basel II on Lending to Small- and Medium-Sized Firms: A Regulatory Policy Assessment Based on Spanish Credit Register Data , 2004 .

[9]  Francesco Ciampi,et al.  Using Economic-Financial Ratios for Small Enterprise Default Prediction Modeling: An Empirical Analysis , 2008 .

[10]  R. Cook.  Generalized Linear Model , 2005 .

[11]  Alan Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[12]  E. Altman,et al.  ZETATM analysis A new model to identify bankruptcy risk of corporations , 1977 .

[13]  Laurens de Haan,et al.  Safety First Portfolio Selection, Extreme Value Theory and Long Run Asset Risks , 1994 .

[14]  T. C. Wilson,et al.  Portfolio Credit Risk , 1998 .

[15]  S. Roberts.  EXTREME VALUE STATISTICS FOR NOVELTY DETECTION IN BIOMEDICAL DATA PROCESSING , 2000 .

[16]  R. O. Edmister,et al.  JOURNAL OF FINANCIAL AND QUANTITATIVE ANALYSIS March 1972 AN EMPIRICAL TEST OF FINANCIAL RATIO ANALYSIS FOR SMALL BUSINESS FAILURE PREDICTION , 2009 .

[17]  Paul Embrechts,et al.  Extreme Value Theory: Potential And Limitations As An Integrated Risk Management Tool , 2000 .

[18]  Gholamreza Nakhaeizadeh,et al.  Machine learning and statistics: the interface , 1996 .

[19]  R. Fisher,et al.  Limiting forms of the frequency distribution of the largest or smallest member of a sample , 1928, Mathematical Proceedings of the Cambridge Philosophical Society.

[20]  Adrian G. Barnett,et al.  An Introduction to Generalized Linear Models, Third Edition , 1990 .

[21]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[22]  Niall M. Adams,et al.  Defining attributes for scorecard construction in credit scoring , 2000 .

[23]  A. Jenkinson.  The frequency distribution of the annual maximum (or minimum) values of meteorological elements , 1955 .

[24]  S. Nadarajah,et al.  Extreme Value Distributions: Theory and Applications , 2000 .

[25]  K. Dowd.  Measuring Market Risk , 2002 .

[26]  Holger Rootzén,et al.  Extreme Values in Finance, Telecommunications, and the Environment , 2003 .

[27]  M. Dietsch,et al.  Should SME exposures be treated as retail or corporate exposures? A comparative analysis of default probabilities and asset correlations in French and German SMEs , 2004 .

[28]  R. L. Prentice,et al.  A case-cohort design for epidemiologic cohort studies and disease prevention trials , 1986 .

[29]  S. Resnick,et al.  Extreme Value Theory as a Risk Management Tool , 1999 .

[30]  R. C. Merton,et al.  On the Pricing of Corporate Debt: The Risk Structure of Interest Rates , 1974, World Scientific Reference on Contingent Claims Analysis in Corporate Finance.

[31]  Giampaolo Gabbi,et al.  Default and Asset Correlation: An Empirical Study for Italian SMEs , 2010 .

[32]  Ely Dahan,et al.  An Extreme-Value Model of Concept Testing , 2001 .

[33]  Gary King,et al.  Logistic Regression in Rare Events Data , 2001, Political Analysis.

[34]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[35]  Steven R. Lerman,et al.  The Estimation of Choice Probabilities from Choice Based Samples , 1977 .

[36]  J. Hüsler,et al.  Laws of Small Numbers: Extremes and Rare Events , 1994 .

[37]  C. Schär,et al.  A PRECIPITATION CLIMATOLOGY OF THE ALPS FROM HIGH-RESOLUTION RAIN-GAUGE OBSERVATIONS , 1998 .

[38]  Edward I. Altman,et al.  FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY , 1968 .

[39]  J. Corcoran.  Modelling Extremal Events for Insurance and Finance , 2002 .

[40]  Charles F. Manski,et al.  Estimation of Response Probabilities From Augmented Retrospective Observations , 1985 .