Rethinking Risk Measurement and Reporting: v. 1

Table of Contents:
About the Editor About the Authors Foreword Introduction PART I AN INTRODUCTION TO BAYESIAN ANALYSIS 1 On Bayesian Data Analysis Christian P. Robert, Judith Rousseau Universite Paris-Dauphine 2 On Computational Tools for Bayesian Data Analysis Christian P. Robert; Jean-Michel Marin Universite Paris-Dauphine; Universite Montpellier 2 3 Bayesian Analysis of the Normal Regression Model Ioannis Ntzoufras Athens University of Economics and Business 4 Market Correlations in the Euro Changeover Period with a View to Portfolio Management Gernot Muller Technische Universitat Munchen 5 Robustification of Bayesian Portfolio Allocation Katrin Schottle; Ralf Werner; Rudi Zagst MEAG MUNICH ERGO AssetManagement GmbH; Deutsche Pfandbriefbank AG; Technische Universitat Munchen PART II EXPERT JUDGEMENT 6 Eliciting Univariate Probability Distributions Jeremy E. Oakley University of Sheffield 7 Eliciting Multivariate Probability Distributions Alireza Daneshkhah; Jeremy E. Oakley University of Strathclyde; University of Sheffield 8 Multiple Dependent Experts' Opinions: An Illustration from Operational-Risk Measurement Jean-Philippe Peters Deloitte PART III STRESS TESTING, DEPENDENCE MODELLING, RISK AGGREGATION AND ALLOCATION 9 A Bayesian Approach to Coherent Stress Testing Riccardo Rebonato Royal Bank of Scotland, Risk Management and Quantitative Analytics, Oxford University, Imperial College, London 10 The Limits of Securitisation: Micro-correlations, Fat Tails and Tail Dependence Carolyn Kousky; Roger M. Cooke Resources for the Future; Resources for the Future and Delft University of Technology 11 Vines and Continuous Non-parametric Bayesian Belief Nets with Emphasis on Model Learning Dorota Kurowicka; Roger M. Cooke Delft University of Technology; Resources for the Future and Delft University of Technology 12 Bayesian Risk Aggregation: Correlation Uncertainty and Expert Judgement Klaus Bocker, Alessandra Crimmi; Holger Fink Risk Analytics and Methods, UniCredit Group; Technische Universitat Munchen 13 Bayesian Approaches for Portfolio Construction: A Review Daniel Giamouridis Athens University of Economics and Business and Cass Business School PART IV REPORTING, DECISION MAKING AND REGULATION 14 Regulators under Uncertainty: The Impact of Model Uncertainty and Information Asymmetry An Chen; Xia Su University of Bonn; Commerzbank 15 The Psychology of Risk Management Gaelle Villejoubert, Frederic Vallee-Tourangeau Kingston University 16 What Is Risk? Towards a Unifying Approach Terje Aven University of Stavanger, Norway 17 Amalgamating Bayesian Experts: A Sceptical View Joseph B. Kadane Carnegie Mellon University 18 The Model and the Manager: Risks Identified and Resolved? Sebastian Fritz-Morgenthal HSH Nordbank, Hamburg 19 Re-Thinking Valuation: The Credit Crisis, Illiquid Markets and Model Risk Dan Rosen R2 Financial Technologies 20 Why Banks Failed the Stress Test Andrew G. Haldane Bank of England

About the Author :
Klaus Bocker Klaus Bocker works as a senior risk controller in UniCredit Group and is the team head of Risk Analytics and Methods. In this capacity, one of his primary responsibilities is overseeing all quantitative aspects of UniCredit Group's economic capital model, in particular business risk, real-estate risk, financial investment risk and risk aggregation. Klaus is also a research fellow at the Center for Mathematical Sciences at the Technische Universitat Munchen. He is conducting research in various fields of finance where he has authored and co-authored several articles that have been published in various recognized finance and mathematical journals. Klaus is also a frequent speaker at international risk conferences and at seminars about risk management and quantitative finance. In 2007, 2008 and 2010, he won the PRMIA Institute's Award for New Frontiers in Risk Management related to his research activities. In August 2007, Klaus was inducted by his peers as a charter member of the international Risk Who's Who honor society. He holds a degree in Theoretical Physics and a PhD in Mathematics from the Technische Universitat Munchen.

Review :
"This volume offers the reader an introduction to Bayesian analysis followed by the consideration of techniques for eliciting and weighting expert judgments. Incorporating seasoned judgment and a greater appreciation of what we do not and cannot know about the future will be a long and arduous journey, but as the Chinese philosopher Lao-tzu said: "A journey of a thousand miles begins with a single step." Hopefully, this book represents a first step on this much needed transformation of the practice of risk management." David M. Rowe, Risk Advisory "Rethinking Risk Measurement and Reporting is an important new collection of essays thst should have a significant impact on the practice of risk management in many fields. In particular, as the world tries to learn the lessons of the global financial crisis of 2007-9 this book should be required reading for both regulatory agencies and financial institutions. Klaus Bocker has created a well-organised and balanced development, with chapters written by some outstanding thinkers and researchers. His ?Introduction' displays his own careful thought and makes a powerful case for adopting the tools of Bayesian analysis and expert judgement. The over-arching theme is uncertainty: uncertainty as the driver of risk, uncertainty and probability as the language of Bayesian statistics, and the role of expert judgement in quantifying and mitigating uncertainty. Risk is a multidisciplinary field, and Rethinking Risk Measurement and Reporting will be of interest to statisticians, psychologists and mathematical modellers, as well as to risk professionals." Tony O'Hagan, University of Sheffield "The current financial crisis is a wake up call for risk measurement methodology. This book takes up the gauntlet and presents a broad array of papers addressing issues from the realm of uncertainty and risk relevant for banking and finance. As to be expected, the Bayesian paradigm figures prominently. Risk managers from academia to practice will highly welcome this volume." Paul Embrechts, Director of RiskLab, ETH Zurich. "The financial crisis has clearly shown the dangers of overreliance on pure quantitative models, and there is now a widespread awareness that algorithms must be carefully calibrated through expert judgement. Yet, the latter has weaknesses of its own, unless managed through appropriate techniques and schemes. Award-winner Klaus Bocker, following his path-breaking contributions on Bayesian analysis in risk aggregation, now provides a rigorous yet refreshing book on how risk should be conceived and dealt with in financial institutions: definitely a must-read for those looking for new ideas to revive the dented axioms of risk management." Andrea Resti, Bocconi University "Of the many failings of risk management prior to the crisis of 2007-09, the neglect of parameter uncertainty is perhaps the least forgivable because this uncertainty could have been measured and recognized ex-ante and with available data. Practitioners will find in this book a variety of practicable approaches to rigorous estimation and robust treatment of parameter uncertainty and other forms of model risk." Michael Gordy "Bayesian analysis allows us to consider uncertainty in a rich and subtle way. We are all used to essential unpredictability, but we can also use probability theory to express our doubts about appropriate values for parameters in our models. Then the Bayesian approach goes deeper: encouraging us to confront our ignorance about how the world works and how well our models might be able to mimic what is going on. This book brings together the best researchers into how these deep ideas can benefit financial risk management." David Spiegelhalter, Winton Professor of the Public Understanding of Risk, University of Cambridge