Application of extreme value theory to economic capital. This book sets out to bridge the gap between the existing theory. Pdf we provide an overview of the role of extreme value theory evt in risk management rm, as a. He himself and his work is very influential in the banking, finance and insurance industries. Embrechts p, extremes and insurance, 28 astin colloquium 1997 more examples. Providing an overview of extreme value theory from. Math 1979 university of antwerp, belgium licentiaat in mathematics 1975 2. Notes on the application of extreme value theory 16 september 2002 this note describes how to apply certain results from extreme value statistical theory evt to problems arising at cfsi. A standard dataset in extreme value theory concerns ows of the river nidd. Integrated approaches to risk measurement in the financial services industry atlanta, ga, 1997. Numerous examples and counterexamples highlight the applicability of the main results obtained.
Kupiec dynamic portfolio replication using stochastic programming m. There are a number of texts available on extreme value theory evt. This text examines the complex issues that concern the stability of the global financial system by presenting a mix of theory and practice. Extreme value theory as a risk management tool paul embrechts. In this white paper we show how extreme value theory can. As the authors admit even as extensive as it is the. We will gradually add to the available slide deck over time. Using extreme value theory to model the multivariate distribution tails. It is authoritative and extremely well writtena nice feature of embrechts et al is an opening 20page reader guideline that gives an overview of the material before the start of the main text. The following concept will be important in the proofs. Properties of risk measures for extreme risks have become an important topic of research. Extreme value theory as a risk management tool casualty. Multivariate extreme value theory recall the rickandsbalkemade haan theorem d 1 question. If one is concerned with the tail of a random variables distribution, then more robust predictions can be obtained.
There are several approaches for the estimation of var, such as historical simulation, the variancecovariance and the monte carlo approaches. Pdf extreme value theory as a risk management tool. Multivariate extremes and the aggregation of dependent. Originally conceived as a onenumber summary of short term market risk, it is now being used in many dierent risk management systems like credit. Denition 9 a function gdened in a right neighborhood of 0 has regular variation at 0 written g2 rv0. Education catholic university of leuven, belgium dr. Mcneil, rudiger frey and paul embrechts, published by princeton university press in 2015. Statistical extreme value theory and its applications the base text. We first use monte carlo simulation to compute a probability distribution for the portfolio loss. Stuart coless book on the modeling of extreme values provides an introductory text on the topic. North american actuarial journal volume 3, 1999 issue 2.
Quantitative risk management concepts, techniques and. Concepts, techniques, and tools, princeton series in finance. Pdf high risk scenarios and extremes semantic scholar. Value at risk var plays a central role in risk management. He sits in the boards of several companies and he is a soughtafter speaker in many occasions. An introduction to statistical modeling of extreme values 2001st edition. Some statements on extremes and correlation over the last number of years, regulators have encouraged.
Paul is very well known for his deep contributions to extreme value theory and quantitative risk management. It could form the basis for an advanced course on multivariate extreme value theory or a course on mathematical issues underlying risk. This new methodology is based on extreme value theory peaksover. I think extreme value theory in general is an important statistical area, since in practice one may be forced to deal with analyzing extreme events, such as in financial engineering, environmental or climate analysis, or. Extreme correlation of international equity markets. Extreme value theory evt is a branch of statistics that deals with such rare situationsand that gives a scienti. Modelling extremal events for insurance and finance. Quantitative risk management princeton university press.
Mcneil, rudiger frey and paul embrechts 2005 quantitative risk management. Extreme value theory plays an important methodological role within risk. Using extreme value theory to model the multivariate distribution tails, we derive the distribution of extreme correlation for a wide class of return distributions. Using extreme value theory, we examine the properties of the hidden tail and calculate its moments of order p. Pdf extreme value theory for risk managers researchgate.
A more technical chapter addresses credit derivatives. We then use extreme value theory evt to study the tail of this loss distribution. This high risk level corresponds to rare events for which it is difficult or impossible to obtain data. An introduction to statistical modeling of extreme values.
Potential and limitations as an integrated risk management tool 2000 cached. There have been many excellent texts written on extreme value theory but none this extensive. Note that we do not yet provide slides for the whole book. In the present paper we discuss sub and superadditivity of quantile based risk measures and show how multivariate extreme value theory yields the ideal modeling environment. Introduction without any doubt, value atrisk var thinking has revolutionised integrated risk management irm, both at the quantitative obvious and at the qualitative not so obvious level. Slides for instructors can be downloaded from our public github repository. It includes extensive discussion of dynamic volatility models, extreme value theory, copulas and credit risk. An extrememly important application of extreme value theory to reinsurance pricing. Section 3 presents the onedimensional theory of extremes, whereas section 4 is concerned with the multivariate case. In this white paper we show how extreme value theory can literally save your neck. It estimates how much a set of investments might lose with a given probability, given normal market conditions, in a set time period such as a day. Paul wilmott on quantitative finance, chapter 19, value at risk var. This much awaited book presents a comprehensive development of extreme value methodology for random walk models, time series, certain types of continuoustime stochastic processes and compound poisson processes, all models which standardly occur in applications in insurance mathematics and mathematical.
Embrechts, p, walk, h recursive estimation of distributional fixpoints journal of applied probability 37, 7387 postscript, pdf. Qrm tutorial is a collection of learning materials for students of quantitative risk management as applied in the financial industry. I believe that this work may become the book on quantitative risk management. Potential and limitations as an integrated risk management tool by paul embrechts of eth zurich 182k pdf 12 pages january 2000. These materials are based on the book quantitative risk management. Var, the product of portfolio theory, is used for shortrun daytoday pro. Paul embrechts, jasa, december, 2002 the modeling of extreme values is important to scientists in such fields as hydrology, civil engineering, environmental science, oceanography and finance. View the article pdf and any associated supplements and figures for a period of 48 hours. Follow the links below to see the complete set of available slides or.
We investigate the interactions between tehran stock. Quantitative risk management concepts, techniques and tools a. The book is based on a graduate course on point processes and extremes. Using extreme value theory to model the multivariate distribution tails, we derive the distribution of extreme correlation for a wide class of return distri.
Value at risk analysis of a leveraged swap sanjay srivastava stress testing in a value at risk framework paul h. Follow the links below to see the complete set of available slides or individual chapter files. The method is useful in showing how large a bias one can expect, for a given n, between the visible insample mean and the true statistical mean or higher moments, which is considerable for close to 1. Section 2 starts with an overview of the credit riskspecific issues within quantitative risk management and shows where relevant extreme value theory related questions are being asked. Paul embrechts is professor of mathematics at the swiss federal institute of technology in zurich. Everyday low prices and free delivery on eligible orders. This work presents portfolio var using an approach combining copula functions, extreme value theory evt and garchgjr models. A short introduction to extreme value theory paddy paddam girocas convention 2001 email.
588 897 933 359 1247 611 253 1371 1230 1064 1419 941 740 615 820 601 392 1448 144 1590 334 1145 337 1360 1258 298 608 272 1230 1428 62 1114 1579 789 1427 791 1474 1047 966 1027 13 691 703 1055 837 1475 1464