Credit Risk Modeling using Excel and VBA

by Gunter Loeffler (University of Ulm, Germany); Peter N. Posch (University of Ulm, Germany)

• ISBN13: 9780470031575
• ISBN10: 0470031573
• eBook ISBN(s): 9780470510742
• Edition: DVD
• Format: Hardcover
• Copyright: 2007-06-01
• Publisher: WILEY
• More Book Details
• Purchase Benefits

Summary

In today's increasingly competitive financial world, successful risk management, portfolio management, and financial structuring demand more than up-to-date financial know-how. They also call for quantitative expertise, including the ability to effectively apply mathematical modeling tools and techniques, in this case credit. Credit Risk Modeling using Excel and VBA with DVD provides practitioners with a hands on introduction to credit risk modeling. Instead of just presenting analytical methods it shows how to implement them using Excel and VBA, in addition to a detailed description in the text a DVD guides readers step by step through the implementation. The authors begin by showing how to use option theoretic and statistical models to estimate a borrowers default risk. The second half of the book is devoted to credit portfolio risk. The authors guide readers through the implementation of a credit risk model, show how portfolio models can be validated or used to access structured credit products like CDO's. The final chapters address modeling issues associated with the new Basel Accord.

Author Biography

GUNTER LÖFFLER is professor of finance at the University of Ulm in Germany. His current research interests are on credit risk and empirical finance. Previously, Gunter was assistant professor at Goethe University Frankfurt, and served as an internal consultant in the asset management division of Commerzbank. His Ph.D. in finance is from the University of Mannheim. Gunter has studied at Heidelberg and Cambridge Universities.

PETER N. POSCH is PhD student in finance at the chair of Gunter Löffler. His current research focus is on credit risk and financial econometrics. Peter studied philosophy and economics and holds a Diplom, M.Sc. equivalent, in economics from the University of Bonn.

Table of Contents

Preface	p. xi
Some Hints for Troubleshooting	p. xiii
Estimating Credit Scores with Logit	p. 1
Linking scores, default probabilities and observed default behavior	p. 1
Estimating logit coefficients in Excel	p. 4
Computing statistics after model estimation	p. 8
Interpreting regression statistics	p. 10
Prediction and scenario analysis	p. 13
Treating outliers in input variables	p. 15
Choosing the functional relationship between the score and explanatory variables	p. 19
Concluding remarks	p. 23
Notes and literature	p. 24
Appendix	p. 24
The Structural Approach to Default Prediction and Valuation	p. 27
Default and valuation in a structural model	p. 27
Implementing the Merton model with a one-year horizon	p. 30
The iterative approach	p. 30
A solution using equity values and equity volatilities	p. 34
Implementing the Merton model with a T-year horizon	p. 39
Credit spreads	p. 44
Notes and literature	p. 44
Transition Matrices	p. 45
Cohort approach	p. 46
Multi-period transitions	p. 51
Hazard rate approach	p. 53
Obtaining a generator matrix from a given transition matrix	p. 58
Confidence intervals with the Binomial distribution	p. 59
Bootstrapped confidence intervals for the hazard approach	p. 63
Notes and literature	p. 67
Appendix	p. 67
Prediction of Default and Transition Rates	p. 73
Candidate variables for prediction	p. 73
Predicting investment-grade default rates with linear regression	p. 75
Predicting investment-grade default rates with Poisson regression	p. 78
Backtesting the prediction models	p. 83
Predicting transition matrices	p. 87
Adjusting transition matrices	p. 88
Representing transition matrices with a single parameter	p. 89
Shifting the transition matrix	p. 91
Backtesting the transition forecasts	p. 96
Scope of application	p. 98
Notes and literature	p. 98
Appendix	p. 99
Modeling and Estimating Default Correlations with the Asset Value Approach	p. 103
Default correlation, joint default probabilities and the asset value approach	p. 103
Calibrating the asset value approach to default experience: the method of moments	p. 105
Estimating asset correlation with maximum likelihood	p. 108
Exploring the reliability of estimators with a Monte Carlo study	p. 114
Concluding remarks	p. 117
Notes and literature	p. 117
Measuring Credit Portfolio Risk with the Asset Value Approach	p. 119
A default mode model implemented in the spreadsheet	p. 119
VBA implementation of a default-mode model	p. 122
Importance sampling	p. 126
Quasi Monte Carlo	p. 130
Assessing simulation error	p. 132
Exploiting portfolio structure in the VBA program	p. 135
Extensions	p. 137
First extension: Multi-factor model	p. 137
Second extension: t-distributed asset values	p. 138
Third extension: Random LCDs	p. 139
Fourth extension: Other risk measures	p. 143
Fifth extension: Multi-state modeling	p. 144
Notes and literature	p. 146
Validation of Rating Systems	p. 147
Cumulative accuracy profile and accuracy ratios	p. 148
Receiver operating characteristic (ROC)	p. 151
Bootstrapping confidence intervals for the accuracy ratio	p. 153
Interpreting CAPs and ROCs	p. 155
Brier Score	p. 156
Testing the calibration of rating-specific default probabilities	p. 157
Validation strategies	p. 161
Notes and literature	p. 162
Validation of Credit Portfolio Models	p. 163
Testing distributions with the Berkowitz test	p. 163
Example implementation of the Berkowitz test	p. 166
Representing the loss distribution	p. 167
Simulating the critical chi-squared value	p. 169
Testing modeling details: Berkowitz on subportfolios	p. 171
Assessing power	p. 175
Scope and limits of the test	p. 176
Notes and literature	p. 177
Risk-Neutral Default Probabilities and Credit Default Swaps	p. 179
Describing the term structure of default: PDs cumulative, marginal, and seen from today	p. 180
From bond prices to risk-neutral default probabilities	p. 181
Concepts and formulae	p. 181
Implementation	p. 184
Pricing a CDS	p. 191
Refining the PD estimation	p. 193
Notes and literature	p. 196
Risk Analysis of Structured Credit: CDOs and First-to-Default Swaps	p. 197
Estimating CDO risk with Monte Carlo simulation	p. 197
The large homogeneous portfolio (LHP) approximation	p. 201
Systematic risk of CDO tranches	p. 203
Default times for first-to-default swaps	p. 205
Notes and literature	p. 209
Appendix	p. 209
Basel II and Internal Ratings	p. 211
Calculating capital requirements in the Internal Ratings-Based (IRB) approach	p. 211
Assessing a given grading structure	p. 214
Towards an optimal grading structure	p. 220
Notes and literature	p. 223
Visual Basics for Applications (VBA)	p. 225
Solver	p. 233
Maximum Likelihood Estimation and Newton's Method	p. 239
Testing and Goodness of Fit	p. 245
User-Defined Functions	p. 251
Index	p. 257
Table of Contents provided by Ingram. All Rights Reserved.