Energy Risk Modelling : Applied Modelling Methods for Risk Managers

by Lewis, Nigel Da Costa

• ISBN13: 9781403934000
• ISBN10: 1403934002
• Format: Hardcover
• Copyright: 2005-09-17
• Publisher: Palgrave Macmillan

Summary

This book is a practitioner's guide for readers who already have a basic understanding of risk management. Statistical ideas are presented by detailing the necessary concepts and outlining how these methods can be implemented. The book differentiates itself from other energy risk books on the market by providing practical examples of how statistical methods are used to solve issues faced in energy risk management.

Author Biography

Nigel Da Costa Lewis is Senior Quantitative Analyst with responsibility for statistical methods at AIG Trading group Inc.

Table of Contents

List of Tables	xi
List of Figures	xiii
Preface	xviii
1 The Statistical Nature of Energy Risk Modeling	1	(20)
1.1 Historical evolution of energy	2	(2)
1.2 Financial risks of energy	4	(2)
1.3 The role of economics — elements of price theory	6	(7)
1.4 Energy markets and products	13	(2)
1.5 The science of energy risk modeling	15	(1)
1.6 Further reading and resources	16	(5)
Part I Statistical Foundations of Energy Risk Modeling
2 Introduction to Applied Probability for Energy Risk Management	21	(20)
2.1 Describing random events	21	(2)
2.2 What is probability?	23	(6)
2.3 Probability functions	29	(5)
2.4 The normal distribution	34	(2)
2.5 Relevance of probability for energy risk management	36	(2)
2.6 A probabilistic model for energy price risk	38	(1)
2.7 Summary	39	(1)
2.8 Further reading	40	(1)
2.9 Review questions	40	(1)
3 Descriptive Statistics of Energy Prices and Returns	41	(12)
3.1 Measures of central tendency	41	(3)
3.2 Measures of dispersion	44	(2)
3.3 A normally distributed model for energy price risk	46	(1)
3.4 Measures of shape	47	(3)
3.5 Relevance of descriptive statistics	50	(1)
3.6 Summary	51	(1)
3.7 Further reading	52	(1)
3.8 Review questions	52	(1)
4 Inferential Statistical Methods for Energy Risk Managers	53	(12)
4.1 What is a hypothesis?	53	(1)
4.2 What is the point of hypothesis testing?	54	(1)
4.3 Refuting chance and controlling errors	55	(1)
4.4 A step by step guide to conducting a hypothesis test	56	(5)
4.5 Confidence intervals	61	(1)
4.6 Summary	61	(1)
4.7 Further reading	62	(1)
4.8 Review questions	62	(3)
Part II Applied Modeling: Techniques and Applications
5 Modeling and Fitting Price Distributions	65	(42)
5.1 Developing a simple model for energy returns	65	(2)
5.2 Using descriptive statistics to assess the model	67	(6)
5.3 Using inferential statistics to aid model construction	73	(2)
5.4 What to do when normality fails?	75	(9)
5.5 Building models using mixture distributions	84	(6)
5.6 General approaches for estimating parameters	90	(11)
5.7 Summary	101	(4)
5.8 Further reading	105	(1)
5.9 Review questions	106	(1)
6 Nonparametric Density Estimation for Energy Price Returns	107	(18)
6.1 Describing energy price data with histograms	108	(7)
6.2 Kernel density estimation	115	(5)
6.3 Explaining empirical distributions to nonstatistical people	120	(3)
6.4 Further reading	123	(1)
6.5 Review questions	123	(2)
7 Correlation Analysis	125	(26)
7.1 Understanding correlation	125	(3)
7.2 Correlation and hedging	128	(1)
7.3 Pearson product moment correlation coefficient	129	(3)
7.4 Spearman rank correlation coefficient	132	(1)
7.5 Spurious correlation	133	(2)
7.6 The Kendall Tau coefficient	135	(1)
7.7 Confidence intervals for the correlation coefficient	135	(1)
7.8 Hypothesis tests of the correlation coefficient	136	(5)
7.9 Coefficient of determination	141	(1)
7.10 Time evolution of correlation coefficients	142	(1)
7.11 Other measures of correlation	143	(5)
7.12 Causation, dependence, and correlation	148	(1)
7.13 Summary	149	(1)
7.14 Further reading	150	(1)
7.15 Review questions	150	(1)
8 A Primer in Applied Regression Analysis	151	(18)
8.1 The simple linear regression model	151	(1)
8.2 Expectation and regression	152	(4)
8.3 Parameter estimation	156	(4)
8.4 Assessing the simple linear regression model	160	(8)
8.5 Summary	168	(1)
8.6 Further reading	168	(1)
8.7 Review questions	168	(1)
9 Multiple Regression and Prediction	169	(10)
9.1 The multiple regression model	169	(1)
9.2 Assessing the multiple regression model	170	(1)
9.3 Prediction	171	(1)
9.4 Building and estimating multiple linear regression models in R	171	(3)
9.5 Multivariate regression	174	(3)
9.6 Summary	177	(1)
9.7 Further reading	177	(1)
9.8 Review questions	178	(1)
10 Misspecification Testing	179	(8)
10.1 Assumptions of linear regression	179	(1)
10.2 Linearity	180	(1)
10.3 Homoscedasticity	181	(1)
10.4 Normality	181	(1)
10.5 Independent variables uncorrelated	181	(1)
10.6 Autocorrelation	182	(1)
10.7 Misspecification testing using R	182	(3)
10.8 Summary	185	(1)
10.9 Further reading	186	(1)
10.10 Review questions	186	(1)
11 Non-linear and Limited Dependent Regression	187	(9)
11.1 Polynomial regression	187	(1)
11.2 Logarithmic, exponential, and more general forms of non-linear regression	188	(1)
11.3 Non-linear regression modeling using R	188	(2)
11.4 Logistic and other limited dependent regression models	190	(5)
11.5 Summary	195	(1)
11.6 Further reading	195	(1)
11.7 Review questions	195	(1)
12 Modeling Energy Price Volatility	196	(17)
12.1 The constant volatility model	196	(4)
12.2 Exponentially weighted moving average models	200	(5)
12.3 Generalized autoregressive conditional hetroscedasticity models	205	(5)
12.4 Summary	210	(1)
12.5 Further reading	210	(2)
12.6 Review questions	212	(1)
13 Stochastic Differential Equations for Derivative Pricing and Energy Risk Management	213	(14)
13.1 What are stochastic differential equations?	213	(5)
13.2 Dealing with jumps in energy prices	218	(3)
13.3 Modeling mean reversion	221	(2)
13.4 Introducing stochastic volatility into energy prices	223	(2)
13.5 Summary	225	(1)
13.6 Further reading	225	(1)
13.7 Review questions	226	(1)
Appendix: Statistical Tables	227	(11)
Notes	238	(4)
Index	242