Bayesian Estimation Under the t-Distribution for Financial Time Series

This chapter studies Student’s t-distribution for fitting serially correlated observations where serial dependence is described by the copula-based Markov chain. Due to the computational difficulty of obtaining maximum likelihood estimates, alternatively, we develop Bayesian inference using the empirical Bayes method through the resampling procedure. We provide a Metropolis–Hastings algorithm to simulate the posterior distribution. We also analyze the stock price data in empirical studies for illustration.

[1]  Takeshi Emura,et al.  A Bayesian inference for time series via copula-based Markov chain models , 2018, Commun. Stat. Simul. Comput..

[2]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[3]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jiwon Kang,et al.  Parameter change tests for ARMA-GARCH models , 2018, Comput. Stat. Data Anal..

[5]  E. S. Page.  CONTINUOUS INSPECTION SCHEMES , 1954 .

[6]  T. Emura,et al.  Estimation under copula-based Markov normal mixture models for serially correlated data , 2019, Commun. Stat. Simul. Comput..

[7]  Jaiwook Baik,et al.  Control charts of mean and variance using copula Markov SPC and conditional distribution by copula , 2019, Commun. Stat. Simul. Comput..

[8]  A. Gelman.  Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper) , 2004 .

[9]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[10]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[11]  J. Rosenthal,et al.  Optimal scaling for various Metropolis-Hastings algorithms , 2001 .

[12]  G. Casella,et al.  The Effect of Improper Priors on Gibbs Sampling in Hierarchical Linear Mixed Models , 1996 .

[13]  R. Kohn,et al.  Markov chain Monte Carlo in conditionally Gaussian state space models , 1996 .

[14]  Eckhard Platen,et al.  Empirical Evidence on Student-t Log-Returns of Diversified World Stock Indices , 2007 .

[15]  Christian P. Robert,et al.  Introducing Monte Carlo Methods with R , 2009 .

[16]  Takeshi Emura,et al.  R routines for performing estimation and statistical process control under copula-based time series models , 2017, Commun. Stat. Simul. Comput..

[17]  E. T. Olsen,et al.  Copulas and Markov processes , 1992 .

[18]  V. H. Lachos,et al.  Extending multivariate-t linear mixed models for multiple longitudinal data with censored responses and heavy tails , 2018, Statistical methods in medical research.

[19]  Anil K. Bera,et al.  A test for normality of observations and regression residuals , 1987 .

[20]  Xiaohong Chen,et al.  Estimation of Copula-Based Semiparametric Time Series Models , 2006 .

[21]  Xin-Wei Huang,et al.  Model diagnostic procedures for copula-based Markov chain models for statistical process control , 2019, Commun. Stat. Simul. Comput..

[22]  Takeshi Emura,et al.  A control chart using copula-based Markov chain models , 2014 .

[23]  Cathy W. S. Chen,et al.  Pair trading based on quantile forecasting of smooth transition GARCH models , 2017 .

[24]  José Dias Curto,et al.  Modeling stock markets’ volatility using GARCH models with Normal, Student’s t and stable Paretian distributions , 2009 .