Slice sampler algorithm for generalized Pareto distribution

Authors : Mohammad ROSTAMİ, Mohd Bakri Adam YAHYA, Mohamed Hisham YAHYA, Noor Akma IBRAHİM

Pages : 1690-1714

View : 24 | Download : 16

Publication Date : 2018-12-12

Article Type : Research Paper

Abstract :In this paper, we developed the slice sampler algorithm for the generalized Pareto distribution insert ignore into journalissuearticles values(GPD); model. Two simulation studies have shown the performance of the peaks over given threshold insert ignore into journalissuearticles values(POT); and GPD density function on various simulated data sets. The results were compared with another commonly used Markov chain Monte Carlo insert ignore into journalissuearticles values(MCMC); technique called Metropolis-Hastings algorithm. Based on the results, the slice sampler algorithm provides closer posterior mean values and shorter $95\%$ quantile based credible intervals compared to the Metropolis-Hastings algorithm. Moreover, the slice sampler algorithm presents a higher level of stationarity in terms of the scale and shape parameters compared with the Metropolis-Hastings algorithm. Finally, the slice sampler algorithm  was employed to estimate the return and risk values of investment in Malaysian gold market.
Keywords : Extreme value theory, Markov chain Monte Carlo, slice sampler, Metropolis Hastings algorithm, Bayesian analysis, gold price