"Dr. Nigel Da Costa Lewis has produced the most exciting volume ever on operational risk modeling. It is a must for students, practitioners, risk managers, and senior executives. . . I feel this work is the first step in revolutionizing the discipline. Other books in this field tell you in theory, there is little difference between theory and practice. Dr. Lewis s work tells you what we all know, in practice, there is."
Dr. O.F. Agbaje, School of Informatics, City University, London
"Dr. Nigel Da Costa Lewis has raised the bar for books on operational risk. His book provides a bridge from the theoretical to the practical, and clears the fog between the buzzwords of operational risk management and the realities of useful modeling tools. The inclusion of numerous concrete examples and solutions will make a broad range of modeling techniques accessible to students of management science. Without a doubt, Dr. Lewis has put quality meat on the bare bones of this important management discipline. He is to be applauded for this magnificent effort."
Prof. Bernard Beecher, Department of Mathematics, City University, New York
"Dr. Nigel Da Costa Lewis has produced one of the most exciting and classic reference volumes on operational risk. As only great teachers can, Dr. Lewis makes even the most obtuse mathematics seem easy and intuitive . . . This book is a must for students, practitioners, and anybody interested in this important subject. In short, it is the most comprehensive and up–to–date textbook on operational risk modeling that I have seen."
Dr. Terence Yiu Wa Chow, Department of Mathematics, University College London, University of London
CHAPTER 1: Introduction to Operational Risk Management and Modeling.
What is Operational Risk?
The Regulatory Environment.
Why a Statistical Approach to Operational Risk Management?
CHAPTER 2: Random Variables, Risk indicators, and Probability.
Random Variables and Operational Risk Indicators.
Types of Random Variable.
Frequency and Subjective Probability.
Case Study 2.1: Downtown Investment Bank.
Case Study 2.2: Mr. Mondey s OPVaR.
Case Study 2.3: Risk in Software Development.
Useful Excel Functions.
CHAPTER 3: Expectation, Covariance, Variance, and Correlation.
Expected Value of a RandomVariable.
Variance and Standard Deviation.
Covariance and Correlation.
Some Rules for Correlation, Variance, and Covariance.
Case Study 3.1: Expected Time to Complete a Complex Transaction.
Case Study 3.2: Operational Cost of System Down Time.
CHAPTER 4: Modeling Central Tendency and Variability of Operational Risk Indicators.
Empirical Measures of Central Tendency.
Measures of Variability.
Case Study 4.1: Approximating Business Risk.
CHAPTER 5: Measuring Skew and Fat Tails of Operational Risk Indicators.
Measuring Fat Tails.
Review of Excel and VBA Functions for Skew and Fat Tails.
CHAPTER 6: Statistical Testing of Operational Risk Parameters.
Objective and Language of Statistical Hypothesis Testing.
Steps Involved In Conducting a Hypothesis Test.
Case Study 6.1: Stephan s Mistake.
Excel Functions for Hypothesis Testing.
CHAPTER 7: Severity of Loss Probability Models.
Estimation of Parameters.
Other Probability Distributions.
What Distribution Best Fits My Severity of Loss Data?
Case Study 7.1: Modeling Severity of Loss Legal Liability Losses.
CHAPTER 8: Frequency of Loss Probability Models.
Popular Frequency of Loss Probability Models.
Other Frequency of Loss Distributions.
Chi–Squared Goodness of Fit Test.
Case Study 8.1: Key Personnel Risk.
CHAPTER 9: Modeling Aggregate Loss Distributions.
Aggregating Severity of Loss and Frequency of Loss Distributions.
Coherent Risk Measures.
CHAPTER 10: The Law of Significant Digits and Fraud Risk Identification.
The Law of Significant Digits.
Benford s Law in Finance.
Case Study 10.1: Analysis of Trader s Profit and Loss Using Benford s Law.
A Step Towards Better Statistical Methods of Fraud Detection.
CHAPTER 11: Correlation and Dependence.
CHAPTER 12: Linear Regression in Operational Risk Management.
The Simple Linear Regression Model.
Polynomial and Other Types of Regression.
Multivariate Multiple Regression.
The Difference Between Correlation and Regression.
A Strategy for Regression Model Building in Operational Risk Management.
CHAPTER 13: Logistic Regression in Operational Risk Management.
Binary Logistic Regression.
Bivariate Logistic Regression.
Case Study 13.1: Nostro Breaks and Volume in a Bivariate Logistic Regression.
Other Approaches for Modeling Bivariate Binary Endpoints.
CHAPTER 14: Mixed Dependent Variable Modeling.
A Model for Mixed Dependent Variables.
Working Assumption of Independence.
Understanding the Benefits of Using a WAI.
Case Study 14.1: Modeling Failure in Compliance.
CHAPTER 15: Validating Operational Risk Proxies Using Surrogate Endpoints.
The Need for Surrogate Endpoints in OR Modeling.
The Prentice Criterion.
Limitations of the Prentice Criterion.
The Real Value Added of Using Surrogate Variables.
Validation Via the Proportion Explained.
Limitations of Surrogate Modelling in Operational Risk Management.
Case Study 15.1: Legal Experience as a Surrogate Endpoint for Legal Costs for a Business Unit.
CHAPTER 16: Introduction to Extreme Value Theory.
Fisher–Tippet Gnedenko Theorem.
Method of Block Maxima.
Peaks over Threshold Modeling.
CHAPTER 17: Managing Operational Risk with Bayesian Belief Networks.
What is a Bayesian Belief Network?
Case Study 17.1: A BBN Model for Software Product Risk.
Creating a BBN–Based Simulation.
Assessing the Impact of Different Managerial Strategies.
Perceived Benefits of Bayesian Belief Network Modeling.
Common Myths About BBNs The Truth for Operational Risk Management.
CHAPTER 18: Epilogue.
Winning the Operational Risk Argument.
Final Tips on Applied Operational Risk Modeling.
Cumulative Distribution Function of the Standard Normal Distribution.
Student s t Distribution.
About the CD–ROM.