Fat-Tailed Models for Risk Estimation

BILIANA GÜNER, PhD

Assistant Professor of Statistics and Econometrics, inlinezyeinlinein University, Turkey

IVAN MITOV, PhD

Head of Quantitative Research, FinAnalytica

BORYANA RACHEVA-YOTOVA, PhD

President, FinAnalytica

Abstract: Accounting for the likelihood of observing extreme returns and for return asymmetry is paramount in financial modeling. In addition to recognizing essential features of the returns’ temporal dynamics, such as autocorrelations, volatility clustering, and long memory, a successful univariate model employs a distributional assumption flexible enough to accommodate various degrees of skewness and heavy-tailedness. At the same time, a model’s usefulness depends on its scalability and practicality—the extent to which the univariate model can be extended to a multivariate one covering a large number of assets.

Risk models are employed in financial modeling to provide a measure of risk that could be employed in portfolio construction, risk management, and derivatives pricing. A risk model is typically a combination of a probability distribution model and a risk measure. In this entry, we discuss alternatives for building the probability distribution model, as well as the pros and cons of various heavy-tailed distributional choices. Our ...

Get Encyclopedia of Financial Models, 3 Volume Set now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.