A parametric model for distributions with flexible behavior in both tails

Environmetrics - Tập 32 Số 2 - 2021
Michael L. Stein1
1Department of Statistics, Rutgers University, Piscataway, New Jersey, USA

Tóm tắt

SummaryFor many problems of inference about a marginal distribution function, while the entire distribution is important, extreme quantiles are of particular interest because rare outcomes may have large consequences. In some applications, only the extreme upper quantiles require extra attention, but in, for example, climatological applications, extremes in both tails of the distribution can be impactful. A possible approach in this setting is to use parametric families of distributions that have flexible behavior in both tails. One way to quantify this property is to require that, for any two generalized Pareto distributions, there is a member of the parametric family that behaves like one of the generalized Pareto distributions in the upper tail and like the negative of the other generalized Pareto distribution in the lower tail. This work proposes some specific quantifications of this notion and describes parametric families of distributions that satisfy these specifications. The proposed families all have closed form expressions for their densities and, hence, are convenient for use in practice. A simulation study shows how one of the proposed families can work well for estimating all quantiles when both tails of a distribution are heavy tailed. An application to climate model output shows this family can also work well when applied to daily average January temperature near Calgary, for which the evolving distribution over time due to climate change is difficult to model accurately by any standard parametric family.

Từ khóa


Tài liệu tham khảo

10.1080/01621459.2019.1617152

10.1017/CBO9780511721434

10.1007/s10687-008-0068-0

10.1007/s13253-019-00369-z

10.1214/11-STS376

10.1111/j.2517-6161.1990.tb01796.x

Haan L., 2007, Extreme value theory: An introduction

10.1111/j.1751-5823.2005.tb00254.x

10.1111/1467-9876.00113

10.1023/A:1024072610684

10.1214/ss/1028905934

10.1016/j.jspi.2010.03.029

10.1023/A:1020925908039

10.1214/aos/1176346596

10.1175/JCLI-D-17-0782.1

10.1080/02626668509490973

10.1016/j.insmatheco.2011.08.013

10.1002/env.2543

10.1016/S0309-1708(02)00056-8

10.1175/1520-0442(2000)013<3760:CITEIA>2.0.CO;2

10.1007/978-0-8176-8134-0

10.1093/biomet/93.2.451

10.1002/2015WR018552

10.1016/j.jspi.2012.07.001

10.5194/ascmo-3-33-2017

Revels J. Lubin M. &Papamarkou T.(2016).Forward‐mode automatic differentiation in Julia.Oxford England: arxiv.

10.3150/bj/1161614952

10.1002/env.2529

10.1002/2015GL064546

10.1093/biomet/asw070

10.1007/s10687-020-00378-z

10.1214/19-STS730

Tencaliec P., 2019, Flexible semiparametric generalized Pareto modeling of the entire range of rainfall amount, Environmetrics, 31, e2582, 10.1002/env.2582

Yadav R. Huser R. &Opitz T.(2019). Spatial hierarchical modeling of threshold exceedances using rate mixtures.arXiv preprint arXiv:1912.04571.

Thông tin
Thông tin xuất bản

Environmetrics

Tập 32 Số 2

Thông tin tác giả