Bayesian and non-Bayesian analysis of the seemingly unrelated regression model with Student-t errors, and its application for forecasting

Arnold Zellner, Tomohiro Ando

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

A description of computationally efficient methods for the Bayesian analysis of Student-t seemingly unrelated regression (SUR) models with unknown degrees of freedom is given. The method combines a direct Monte Carlo (DMC) approach with an importance sampling procedure to calculate Bayesian estimation and prediction results using a diffuse prior. This approach is employed to compute Bayesian posterior densities for the parameters, as well as predictive densities for future values of variables and the associated moments, intervals and other quantities that are useful to both forecasters and others. The results obtained using our approach are compared to those yielded by the use of DMC for a standard normal SUR model.

Original languageEnglish
Pages (from-to)413-434
Number of pages22
JournalInternational Journal of Forecasting
Volume26
Issue number2
DOIs
Publication statusPublished - 2010 Apr

Fingerprint

Regression model
Seemingly unrelated regression
Predictive density
Bayesian analysis
Importance sampling
Bayesian estimation
Prediction

Keywords

  • Direct Monte Carlo
  • Heavy tail behavior
  • Importance sampling
  • Markov chain Monte Carlo

ASJC Scopus subject areas

  • Business and International Management

Cite this

Bayesian and non-Bayesian analysis of the seemingly unrelated regression model with Student-t errors, and its application for forecasting. / Zellner, Arnold; Ando, Tomohiro.

In: International Journal of Forecasting, Vol. 26, No. 2, 04.2010, p. 413-434.

Research output: Contribution to journalArticle

@article{2e812a73de504a6a8a0cd7771ac42d66,
title = "Bayesian and non-Bayesian analysis of the seemingly unrelated regression model with Student-t errors, and its application for forecasting",
abstract = "A description of computationally efficient methods for the Bayesian analysis of Student-t seemingly unrelated regression (SUR) models with unknown degrees of freedom is given. The method combines a direct Monte Carlo (DMC) approach with an importance sampling procedure to calculate Bayesian estimation and prediction results using a diffuse prior. This approach is employed to compute Bayesian posterior densities for the parameters, as well as predictive densities for future values of variables and the associated moments, intervals and other quantities that are useful to both forecasters and others. The results obtained using our approach are compared to those yielded by the use of DMC for a standard normal SUR model.",
keywords = "Direct Monte Carlo, Heavy tail behavior, Importance sampling, Markov chain Monte Carlo",
author = "Arnold Zellner and Tomohiro Ando",
year = "2010",
month = "4",
doi = "10.1016/j.ijforecast.2009.12.012",
language = "English",
volume = "26",
pages = "413--434",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Bayesian and non-Bayesian analysis of the seemingly unrelated regression model with Student-t errors, and its application for forecasting

AU - Zellner, Arnold

AU - Ando, Tomohiro

PY - 2010/4

Y1 - 2010/4

N2 - A description of computationally efficient methods for the Bayesian analysis of Student-t seemingly unrelated regression (SUR) models with unknown degrees of freedom is given. The method combines a direct Monte Carlo (DMC) approach with an importance sampling procedure to calculate Bayesian estimation and prediction results using a diffuse prior. This approach is employed to compute Bayesian posterior densities for the parameters, as well as predictive densities for future values of variables and the associated moments, intervals and other quantities that are useful to both forecasters and others. The results obtained using our approach are compared to those yielded by the use of DMC for a standard normal SUR model.

AB - A description of computationally efficient methods for the Bayesian analysis of Student-t seemingly unrelated regression (SUR) models with unknown degrees of freedom is given. The method combines a direct Monte Carlo (DMC) approach with an importance sampling procedure to calculate Bayesian estimation and prediction results using a diffuse prior. This approach is employed to compute Bayesian posterior densities for the parameters, as well as predictive densities for future values of variables and the associated moments, intervals and other quantities that are useful to both forecasters and others. The results obtained using our approach are compared to those yielded by the use of DMC for a standard normal SUR model.

KW - Direct Monte Carlo

KW - Heavy tail behavior

KW - Importance sampling

KW - Markov chain Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=77649270010&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649270010&partnerID=8YFLogxK

U2 - 10.1016/j.ijforecast.2009.12.012

DO - 10.1016/j.ijforecast.2009.12.012

M3 - Article

AN - SCOPUS:77649270010

VL - 26

SP - 413

EP - 434

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 2

ER -