Regression-type analysis for block maxima on block maxima

This paper devises a regression-type model for the situation where both the response and covariates are extreme. The proposed approach is designed for the setting where both the response and covariates are themselves block maxima, and thus contrarily to standard regression methods it takes into account the key fact that the limiting distribution of suitably standardized componentwise maxima is an extreme value copula. An important target in the proposed framework is the regression manifold, which consists of a family of regression lines obeying the latter asymptotic result. To learn about the proposed model from data, we employ a Bernstein polynomial prior on the space of angular densities which leads to an induced prior on the space of regression manifolds. Numerical studies suggest a good performance of the proposed methods, and a finance real-data illustration reveals interesting aspects on the comovements of extreme losses between two leading stock markets.

[1]  R. Koenker,et al.  Regression Quantiles , 2007 .

[2]  Chih-Ling Tsai,et al.  Tail Index Regression , 2009 .

[3]  Jonathan M. Borwein,et al.  Meetings with Lambert W and Other Special Functions in Optimization and Analysis , 2016 .

[4]  M. Haugh,et al.  An Introduction to Copulas , 2016 .

[5]  Jonathan A. Tawn,et al.  Modelling non‐stationary extremes with application to surface level ozone , 2009 .

[6]  H. Joe Multivariate extreme value distributions , 1997 .

[7]  Yizao Wang,et al.  Conditional sampling for spectrally discrete max-stable random fields , 2010, Advances in Applied Probability.

[8]  Jonathan A. Tawn,et al.  Exploiting occurrence times in likelihood inference for componentwise maxima , 2005 .

[9]  Anthony C. Davison,et al.  Statistics of Extremes , 2015, International Encyclopedia of Statistical Science.

[10]  Christine M. Anderson-Cook,et al.  Book review: quantitative risk management: concepts, techniques and tools, revised edition, by A.F. McNeil, R. Frey and P. Embrechts. Princeton University Press, 2015, ISBN 978-0-691-16627-8, xix + 700 pp. , 2017, Extremes.

[11]  Anthony Ledford,et al.  A new class of models for bivariate joint tails , 2009 .

[12]  Naomi S. Altman,et al.  Quantile regression , 2019, Nature Methods.

[13]  Johan Segers,et al.  Peaks over thresholds modelling with multivariate generalized Pareto distributions , 2016, 1612.01773.

[14]  Peter K. Dunn,et al.  Randomized Quantile Residuals , 1996 .

[15]  L. Haan,et al.  Extreme value theory : an introduction , 2006 .

[16]  Eric P. Smith,et al.  An Introduction to Statistical Modeling of Extreme Values , 2002, Technometrics.

[17]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[18]  Richard W. Katz,et al.  Statistical Methods for Nonstationary Extremes , 2013 .

[19]  T. Yee,et al.  Vector generalized linear and additive extreme value models , 2007 .

[20]  S. Resnick,et al.  Limit theory for multivariate sample extremes , 1977 .

[21]  T. Hanson,et al.  Bernstein polynomial angular densities of multivariate extreme value distributions , 2017 .

[22]  Ana Isabel Garralda Guillem Structure de dépendance des lois de valeurs extrêmes bivariées , 2000 .

[23]  Testing asymptotic independence in bivariate extremes , 2009 .

[24]  J. Corcoran Modelling Extremal Events for Insurance and Finance , 2002 .

[25]  Richard A. Davis,et al.  Approximating the conditional density given large observed values via a multivariate extremes framework, with application to environmental data , 2012, 1301.1428.

[26]  V. Chernozhukov Extremal quantile regression , 2005, math/0505639.

[27]  V. Chavez-Demoulin,et al.  Causal mechanism of extreme river discharges in the upper Danube basin network , 2019, Journal of the Royal Statistical Society: Series C (Applied Statistics).

[28]  Johan Segers,et al.  Extreme-value copulas , 2009, 0911.1015.

[29]  F. Longin,et al.  Extreme Events in Finance : A Handbook of Extreme Value Theory and Its Applications , 2016 .