Credit Risk Stress Testing for Eu15 Banks: A Model Combination Approach

In bank stress tests, the role of a satellite model is to tie bank-specific risk variables to macroeconomic variables that can generate stress. For valid stress tests it is important to develop a comprehensive satellite model that both preserves the sense of known economic relationships and also exhibits high predictive ability. However, it is often difficult to achieve these desiderata in a single satellite model. Multicollinearity of key macro variables and limited data may militate against inclusion of all important stress variables, thus limiting the range of stress scenarios. In order to address this problem we depart from the custom of using a single model as the "true" satellite. Instead, we generate a full space of candidate models that we then screen for reasonable candidates that remain sufficiently rich to cover a wide range of stress scenarios. We then develop composite models by combining the surviving candidate models through weighting. The result is a composite satellite model that includes all the desired macroeconomic variables, reflects the expected relationships with the dependent variable (NPL growth) and exhibits more than 20% lower RMSE compared to a commonly used benchmark model. An illustrative stress testing application shows that this approach can provide policy makers with prudent estimates of credit risk.

[1]  M. Melecký,et al.  Macroprudential Stress Testing of Credit Risk: A Practical Approach for Policy Makers , 2012 .

[2]  K. Burnham,et al.  Model selection: An integral part of inference , 1997 .

[3]  Jeffrey M. Wooldridge,et al.  Introductory Econometrics: A Modern Approach , 1999 .

[4]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[5]  Sarantis Kalyvitis,et al.  Who Exports High-Quality Products? Some Empirical Regularities from Greek Exporting Firms , 2015, SSRN Electronic Journal.

[6]  J. Stock,et al.  Forecasting with Many Predictors , 2006 .

[7]  Takashi Isogai.  Stress-testing the Banking System: Scenario design and calibration , 2009 .

[8]  Kenneth S. Rogoff,et al.  From Financial Crash to Debt Crisis , 2010 .

[9]  Martin Melecky,et al.  Macroprudential Stress-Testing Practices of Central Banks in Central and Southeastern Europe: Comparison and Challenges Ahead , 2010 .

[10]  E. Charalambakis.  On Corporate Financial Distress Prediction: What Can We Learn from Private Firms in a Small Open Economy? , 2014, SSRN Electronic Journal.

[11]  Frank E. Harrell,et al.  Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis , 2001 .

[12]  Gianni Amisano,et al.  Prediction with Misspecified Models , 2012 .

[13]  C. Schmieder,et al.  Stress Testing Credit Risk: Is the Czech Republic Different from Germany? , 2008 .

[14]  J. Stock,et al.  Forecasting Output and Inflation: The Role of Asset Prices , 2001 .

[15]  A. Vouldis,et al.  Profitability in the Greek Banking System: A Dual Investigation of Net Interest and Non-Interest Income , 2015, SSRN Electronic Journal.

[16]  D. Papageorgiou,et al.  The Macroeconomic Impact of Structural Reforms in Product and Labour Markets: Trade-Offs and Complementarities , 2015, SSRN Electronic Journal.

[17]  Nils Lid Hjort,et al.  Model Selection and Model Averaging , 2001 .

[18]  Adrian E. Raftery,et al.  Bayesian Model Averaging: A Tutorial , 2016 .

[19]  Roberto Perotti.  Fiscal Consolidation in Europe: Composition Matters , 1996 .

[20]  Dimitrios P. Louzis.  Steady-state priors and Bayesian variable selection in VAR forecasting , 2016, SSRN Electronic Journal.

[21]  Antonis Adam,et al.  Industry-Level Labour Demand Elasticities Across the Eurozone: Will There Be Any Gain after the Pain of Internal Devaluation? , 2014, SSRN Electronic Journal.

[22]  Hiona Balfoussia,et al.  Financial conditions and economic activity: the potential impact of the targeted long-term refinancing operations (TLTROs) , 2015, SSRN Electronic Journal.

[23]  Marco Del Negro,et al.  Dynamic Prediction Pools: An Investigation of Financial Frictions and Forecasting Performance , 2014 .

[24]  C. Schmieder,et al.  A Framework for Macroprudential Bank Solvency Stress Testing: Application to S-25 and Other G-20 Country FSAPs , 2013 .

[25]  A. Sarris,et al.  The Distributional Consequences of the Stabilization and Adjustment Policies in Greece During the Crisis, with the Use of a Multisectoral Computable General Equilibrium Model , 2015, SSRN Electronic Journal.

[26]  Martin Scheicher,et al.  Macroeconomic Stress Testing: Preliminary Evidence for Austria , 2002 .

[27]  J. Stock,et al.  A Comparison of Linear and Nonlinear Univariate Models for Forecasting Macroeconomic Time Series , 1998 .

[28]  A. Vouldis,et al.  Macroeconomic and Bank-Specific Determinants of Non-Performing Loans in Greece: A Comparative Study of Mortgage, Business and Consumer Loan Portfolios , 2010, SSRN Electronic Journal.

[29]  Enrique Moral-Benito,et al.  Model Averaging in Economics: An Overview , 2015 .

[30]  A. Timmermann.  Forecast Combinations , 2005 .

[31]  Marco Gross,et al.  A False Sense of Security in Applying Handpicked Equations for Stress Test Purposes , 2015, SSRN Electronic Journal.

[32]  Bruce E. Hansen,et al.  Least-squares forecast averaging , 2008 .

[33]  Leif Anders Thorsrud,et al.  Does Forecast Combination Improve Norges Bank Inflation Forecasts?* , 2012 .

[34]  Allan Timmermann,et al.  Persistence in forecasting performance and conditional combination strategies , 2006 .

[35]  J. Sargan.  THE ESTIMATION OF ECONOMIC RELATIONSHIPS USING INSTRUMENTAL VARIABLES , 1958 .

[36]  Carlo A. Favero,et al.  Model Uncertainty, Thick Modelling and the Predictability of Stock Returns , 2003 .

[37]  Fred L. Collopy,et al.  Error Measures for Generalizing About Forecasting Methods: Empirical Comparisons , 1992 .

[38]  P. Neu,et al.  Liquidity Risk Measurement and Management: A Practitioner's Guide to Global Best Practices , 2011 .

[39]  Matthew T. Jones,et al.  Stress Testing Financial Systems: What to Do When the Governor Calls , 2004, SSRN Electronic Journal.

[40]  David R. Anderson,et al.  Model Selection and Multimodel Inference , 2003 .

[41]  Anastasios Evgenidis,et al.  What are the International Channels Through Which a Us Policy Shock is Transmitted to the World Economies? Evidence from a Time Varying FAVAR , 2015, SSRN Electronic Journal.

[42]  T. Sager,et al.  Systemic Early Warning Systems for Eu15 Based on the 2008 Crisis , 2016, SSRN Electronic Journal.

[43]  Athanasios Tagkalakis.  Fiscal policy, net exports, and the sectoral composition of output in Greece , 2015, SSRN Electronic Journal.

[44]  R. Moessner,et al.  Macroprudential Policy – A Literature Review , 2011 .

[45]  Francisco Vazquezbenjamin M. Tabakmarcos.  A Macro Stress Test Model of Credit Risk for the Brazilian Banking Sector , 2012 .

[46]  Arnold Zellner,et al.  To combine or not to combine? Issues of combining forecasts , 1992 .

[47]  A. Foglia,et al.  Stress Testing Credit Risk: A Survey of Authorities' Approaches , 2008 .

[48]  Christoffer Kok,et al.  A Macro Stress Testing Framework for Assessing Systemic Risks in the Banking Sector , 2013, SSRN Electronic Journal.

[49]  M. Arellano,et al.  Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations , 1991 .

[50]  G. Hondroyiannis,et al.  When Does it Pay to Tax? Evidence from State-Dependent Fiscal Multipliers in the Euro Area , 2015, SSRN Electronic Journal.

[51]  J. Hausman.  Specification tests in econometrics , 1978 .

[52]  Theodoros S. Papaspyrou.  Emu 2.0 Drawing Lessons from the Crisis - a New Framework for Stability and Growth , 2015, SSRN Electronic Journal.

[53]  J. Geweke,et al.  Optimal Prediction Pools , 2008 .

[54]  J. Stock,et al.  Combination forecasts of output growth in a seven-country data set , 2004 .

[55]  Jesús Saurina,et al.  Credit Cycles, Credit Risk, and Prudential Regulation , 2006 .