Bayesian modeling of dynamic extreme values: extension of generalized extreme value distributions with latent stochastic processes. Issue 7 (19th May 2017)

• Record Type: Journal Article
• Authors: Nakajima, Jouchi; Kunihama, Tsuyoshi; Omori, Yasuhiro
• Is Part Of: Journal of applied statistics. Volume 44:Issue 7(2017)
• Page Start: 1248
• Page End: 1268
• Publication Date: 2017-05-19
• Subjects: ARMA process -- electricity demand -- extreme values -- generalized extreme value distribution -- mixture sampler -- stock returns; Statistics -- Periodicals; 519.5
• DOI: 10.1080/02664763.2016.1201796
• Languages: English
• ISSNs: 0266-4763

Abstract

ABSTRACT: This paper develops Bayesian inference of extreme value models with a flexible time-dependent latent structure. The generalized extreme value distribution is utilized to incorporate state variables that follow an autoregressive moving average (ARMA) process with Gumbel-distributed innovations. The time-dependent extreme value distribution is combined with heavy-tailed error terms. An efficient Markov chain Monte Carlo algorithm is proposed using a state-space representation with a finite mixture of normal distributions to approximate the Gumbel distribution. The methodology is illustrated by simulated data and two different sets of real data. Monthly minima of daily returns of stock price index, and monthly maxima of hourly electricity demand are fit to the proposed model and used for model comparison. Estimation results show the usefulness of the proposed model and methodology, and provide evidence that the latent autoregressive process and heavy-tailed errors play an important role to describe the monthly series of minimum stock returns and maximum electricity demand.