Coherent Stress Testing: A Bayesian Approach to the Analysis of Financial Stress / Edition 1 available in Hardcover, eBook
Coherent Stress Testing: A Bayesian Approach to the Analysis of Financial Stress / Edition 1
- ISBN-10:
- 0470666013
- ISBN-13:
- 9780470666012
- Pub. Date:
- 07/13/2010
- Publisher:
- Wiley
Coherent Stress Testing: A Bayesian Approach to the Analysis of Financial Stress / Edition 1
Buy New
$80.00Overview
Based on the author's extensive work, research and presentations in the area, the book fills a gap in quantitative risk management by introducing a new and very intuitively appealing approach to stress testing based on expert judgement and Bayesian networks. It constitutes a radical departure from the traditional statistical methodologies based on Economic Capital or Extreme-Value-Theory approaches.
The book is split into four parts. Part I looks at stress testing and at its role in modern risk management. It discusses the distinctions between risk and uncertainty, the different types of probability that are used in risk management today and for which tasks they are best used. Stress testing is positioned as a bridge between the statistical areas where VaR can be effective and the domain of total Keynesian uncertainty. Part II lays down the quantitative foundations for the concepts described in the rest of the book. Part III takes readers through the application of the tools discussed in part II, and introduces two different systematic approaches to obtaining a coherent stress testing output that can satisfy the needs of industry users and regulators. In part IV the author addresses more practical questions such as embedding the suggestions of the book into a viable governance structure.
Product Details
| ISBN-13: | 9780470666012 |
|---|---|
| Publisher: | Wiley |
| Publication date: | 07/13/2010 |
| Series: | The Wiley Finance Series |
| Pages: | 240 |
| Product dimensions: | 6.60(w) x 9.70(h) x 1.00(d) |
About the Author
Table of Contents
Acknowledgements xi
1 Introduction 1
1.1 Why We Need Stress Testing 1
1.2 Plan of the Book 5
1.3 Suggestions for Further Reading 6
I Data, Models and Reality 7
2 Risk and Uncertainty - or, Why Stress Testing is Not Enough 9
2.1 The Limits of Quantitative Risk Analysis 9
2.2 Risk or Uncertainty? 10
2.3 Suggested Reading 13
3 The Role of Models in Risk Management and Stress Testing 15
3.1 How Did We Get Here? 16
3.2 Statement of the Two Theses of this Chapter 17
3.3 Defence of the First Thesis (Centrality of Models) 18
3.3.1 Models as Indispensable Interpretative Tools 18
3.3.2 The Plurality-of-Models View 21
3.4 Defence of the Second Thesis (Coordination) 23
3.4.1 Traders as Agents 23
3.4.2 Agency Brings About Coordination 25
3.4.3 From Coordination to Positive Feedback 26
3.5 The Role of Stress and Scenario Analysis 27
3.6 Suggestions for Further Reading 29
4 What Kind of Probability Do We Need in Risk Management? 31
4.1 Frequentist versus Subjective Probability 31
4.2 Tail Co-dependence 36
4.3 From Structural Models to Co-dependence 38
4.4 Association or Causation? 39
4.5 Suggestions for Further Reading 42
II The Probabilistic Tools and Concepts 45
5 Probability with Boolean Variables I: Marginal and Conditional Probabilities 47
5.1 The Set-up and What We are Trying to Achieve 47
5.2 (Marginal) Probabilities 50
5.3 Deterministic Causal Relationship 53
5.4 Conditional Probabilities 55
5.5 Time Ordering and Causation 56
5.6 An Important Consequence: Bayes' Theorem 57
5.7 Independence 58
5.8 Two Worked-Out Examples 59
5.8.1 Dangerous Running 59
5.8.2 Rare and Even More Dangerous Diseases 61
5.9 Marginal and Conditional Probabilities: A Very Important Link 62
5.10 Interpreting and Generalizing the Factors xik 65
5.11 Conditional Probability Maps 67
6 Probability with Boolean Variables II: Joint Probabilities 71
6.1 Conditioning on More Than One Event 71
6.2 Joint Probabilities 73
6.3 A Remark on Notation 75
6.4 From the Joint to the Marginal and the Conditional Probabilities 76
6.5 From the Joint Distribution to Event Correlation 77
6.6 From the Conditional and Marginal to the Joint Probabilities? 83
6.7 Putting Independence to Work 84
6.8 Conditional Independence 86
6.9 Obtaining Joint Probabilities with Conditional Independence 88
6.10 At a Glance 89
6.11 Summary 90
6.12 Suggestions for Further Reading 90
7 Creating Probability Bounds 93
7.1 The Lay of the Land 93
7.2 Bounds on Joint Probabilities 93
7.3 How Tight are these Bounds in Practice? 96
8 Bayesian Nets I: An Introduction 99
8.1 Bayesian Nets: An Informal Definition 99
8.2 Defining the Structure of Bayesian Nets 101
8.3 More About Conditional Independence 104
8.4 What Goes in the Conditional Probability Tables? 106
8.5 Useful Relationships 107
8.6 A Worked-Out Example 109
8.7 A Systematic Approach 111
8.8 What Can We Do with Bayesian Nets? 113
8.8.1 Unravelling the Causal Structure 113
8.8.2 Estimating the Joint Probabilities 114
8.9 Suggestions for Further Reading 115
9 Bayesian Nets II: Constructing Probability Tables 117
9.1 Statement of the Problem 117
9.2 Marginal Probabilities - First Approach 118
9.2.1 Starting from a Fixed Probability 119
9.2.2 Starting from a Fixed Magnitude of the Move 120
9.3 Marginal Probabilities - Second Approach 120
9.4 Handling Events of Different Probability 122
9.5 Conditional Probabilities: A Reasonable Starting Point 123
9.6 Conditional Probabilities: Checks and Constraints 125
9.6.1 Necessary Conditions 125
9.6.2 Triplet Conditions 126
9.6.3 Independence 127
9.6.4 Deterministic Causation 127
9.6.5 Incompatibility of Events 128
9.7 Internal Compatibility of Conditional Probabilities: The Need for a Systematic Approach 129
III Applications 131
10 Obtaining a Coherent Solution I: Linear Programming 133
10.1 Plan of the Work Ahead 133
10.2 Coherent Solution with Conditional Probabilities Only 135
10.3 The Methodology in Practice: First Pass 141
10.4 The CPU Cost of the Approach 144
10.5 Illustration of the Linear Programming Technique 144
10.6 What Can We Do with this Information? 149
10.6.1 Extracting Information with Conditional Probabilities Only 149
10.6.2 Extracting Information with Conditional and Marginal Probabilities 151
11 Obtaining a Coherent Solution II: Bayesian Nets 155
11.1 Solution with Marginal and n-conditioned Probabilities 156
11.1.1 Generalizing the Results 164
11.2 An 'Automatic' Prescription to Build Joint Probabilities 165
11.3 What Can We Do with this Information? 167
11.3.1 Risk-Adjusting Returns 168
IV Making It Work In Practice 171
12 Overcoming Our Cognitive Biases 173
12.1 Cognitive Shortcoming and Bounded Rationality 174
12.1.1 How Pervasive are Cognitive Shortcomings? 175
12.1.2 The Social Context 175
12.1.3 Adaptiveness 176
12.2 Representativeness 178
12.3 Quantification of the Representativeness Bias 181
12.4 Causal/Diagnostic and Positive/Negative Biases 182
12.5 Conclusions 184
12.6 Suggestions for Further Reading 185
13 Selecting and Combining Stress Scenarios 187
13.1 Bottom Up or Top Down? 187
13.2 Relative Strengths and Weaknesses of the Two Approaches 187
13.3 Possible Approaches to a Top-Down Analysis 190
13.4 Sanity Checks 191
13.5 How to Combine Stresses - Handling the Dimensionality Curse 192
13.6 Combining the Macro and Bottom-Up Approaches 194
14 Governance 197
14.1 The Institutional Aspects of Stress Testing 197
14.1.1 Transparency and Ease of Use 197
14.1.2 Challenge by Non-specialists 198
14.1.3 Checks for Completeness 198
14.1.4 Interactions among Different Specialists 199
14.1.5 Auditability of the Process and of the Results 201
14.2 Lines of Criticism 201
14.2.1 The Role of Subjective Inputs 202
14.2.2 The Complexity of the Stress-testing Process 203
Appendix: A Simple Introduction to Linear Programming 205
A.1 Plan of the Appendix 205
A.2 Linear Programming - A Refresher 205
A.3 The Simplex Method 208
References 213
Index 217