Much of financial engineering is based on so-called “complete markets” and on the use of the Black-Scholes formula. The formula relies on the assumption that asset prices follow a log-normal distribution, or in other words, the daily fluctuations in prices viewed as percentage changes follow a Gaussian distribution. On the contrary, studies of actual asset prices show that they do not follow a log-normal distribution. In this paper, we investigate several widely-used heavy-tailed distributions. Our results indicate that the Skewed t distribution has the best empirical performance in fitting the Canadian stock market returns. We claim the results are valuable for market participants and the financial industry.

The aim of this study is to analyze the tails of the distributions of stock market returns and to compare the differences between them. It is a well-established fact that the vast majority of stock market return distributions exhibit fat tails (a bigger probability of extreme outcomes then in the case of the normal probability). Apart from that, there seems to be a popular opinion that most market returns are negatively skewed with a fatter left tail. The study utilizes two methods for comparing the tails of a distribution. A simple approached based on the sample kurtosis, with a modification that allows for the calculation of kurtosis separately for the right and the left tail of a single distribution and a more complex approach based on the maximum likelihood fitting of the Generalized Pareto Distribution to both tales of standardized return distributions. The second approach is based on the assumptions of the Extreme Value Theory (EVT) and the Pickands-Balkema-de Haan theorem. Both approaches provide similar conclusions. Results suggest that whether the left or the right tail of the return distribution is bigger varies from market to market. All four major equity indices of the Polish Warsaw Stock Exchange exhibited a fatter left tale. However, in the whole sample it was actually more common for the right tail to be heavier, with 12 indices out of 20 exhibiting a fatter right tail then the left. The sample kurtosis indicated that all stock market return's distributions were heavy tailed, whereas the estimates of Generalized Pareto Distribution parameters did indicate standard or thin tails in two cases. Statistical tests indicate that the differences between the tails of stock market distributions are not statistically significant.

The Tokyo Stock Exchange (TSE) is the fourth largest stock exchange in the world by aggregate market capitalization of its listed companies and largest in East Asia and Asia. It is of great importance for those in charge of managing risk to understand how its market index returns are distributed. The goal of this paper is to examine how various types of heavy-tailed distribution perform in risk management of the N225 Index returns. We compared these heavy-tailed distributions through a variety of criteria. Our results indicate the generalized hyperbolic distribution has the best goodness of fit and generates most suitable risk measures.

As other developed economies over the world, the stock market plays a crucial role in facilitating the economic growth. In this paper, we compare two different types of heavy-tailed distribution, the Student's t distribution and the normal reciprocal inverse Gaussian distribution, within the generalized autoregressive conditional heteroskedasticity (GARCH) framework for the daily stock market returns of South Korea (KOSPI). Our results show two important findings: i) the daily KOSPI returns exhibit conditional heavy tails even after volatility clustering effect has been accounted for; and ii) the NRIG distribution has a better in-sample performance than the Student's t distribution.

A guide to the growing importance of extreme value risk theory, methods, and applications in the financial sector Presenting a uniquely accessible guide, Extreme Events in Finance: A Handbook of Extreme Value Theory and Its Applications features a combination of the theory, methods, and applications of extreme value theory (EVT) in finance and a practical understanding of market behavior including both ordinary and extraordinary conditions. Beginning with a fascinating history of EVTs and financial modeling, the handbook introduces the historical implications that resulted in the applications and then clearly examines the fundamental results of EVT in finance. After dealing with these theoretical results, the handbook focuses on the EVT methods critical for data analysis. Finally, the handbook features the practical applications and techniques and how these can be implemented in financial markets. Extreme Events in Finance: A Handbook of Extreme Value Theory and Its Applications includes: Over 40 contributions from international experts in the areas of finance, statistics, economics, business, insurance, and risk management Topical discussions on univariate and multivariate case extremes as well as regulation in financial markets Extensive references in order to provide readers with resources for further study Discussions on using R packages to compute the value of risk and related quantities The book is a valuable reference for practitioners in financial markets such as financial institutions, investment funds, and corporate treasuries, financial engineers, quantitative analysts, regulators, risk managers, large-scale consultancy groups, and insurers. Extreme Events in Finance: A Handbook of Extreme Value Theory and Its Applications is also a useful textbook for postgraduate courses on the methodology of EVTs in finance.

The new edition of this influential textbook, geared towards graduate or advanced undergraduate students, teaches the statistics necessary for financial engineering. In doing so, it illustrates concepts using financial markets and economic data, R Labs with real-data exercises, and graphical and analytic methods for modeling and diagnosing modeling errors. These methods are critical because financial engineers now have access to enormous quantities of data. To make use of this data, the powerful methods in this book for working with quantitative information, particularly about volatility and risks, are essential. Strengths of this fully-revised edition include major additions to the R code and the advanced topics covered. Individual chapters cover, among other topics, multivariate distributions, copulas, Bayesian computations, risk management, and cointegration. Suggested prerequisites are basic knowledge of statistics and probability, matrices and linear algebra, and calculus. There is an appendix on probability, statistics and linear algebra. Practicing financial engineers will also find this book of interest.