Bayesian inference in generalized error and generalized student-t regression models

Economics

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Bayesian inference in generalized error and generalized student-t regression models. / Tsionas, Michael.
In: Communications in Statistics - Theory and Methods, Vol. 37, No. 3, 2008, p. 388-407.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Tsionas, M 2008, 'Bayesian inference in generalized error and generalized student-t regression models', Communications in Statistics - Theory and Methods, vol. 37, no. 3, pp. 388-407. https://doi.org/10.1080/03610920701653151

APA

Tsionas, M. (2008). Bayesian inference in generalized error and generalized student-t regression models. Communications in Statistics - Theory and Methods, 37(3), 388-407. https://doi.org/10.1080/03610920701653151

Vancouver

Tsionas M. Bayesian inference in generalized error and generalized student-t regression models. Communications in Statistics - Theory and Methods. 2008;37(3):388-407. doi: 10.1080/03610920701653151

Author

Tsionas, Michael. / Bayesian inference in generalized error and generalized student-t regression models. In: Communications in Statistics - Theory and Methods. 2008 ; Vol. 37, No. 3. pp. 388-407.

Bibtex

@article{e1c57f819dbc4358ba1cf83289cf8340,

title = "Bayesian inference in generalized error and generalized student-t regression models",

abstract = "This study takes up inference in linear models with generalized error and generalized t distributions. For the generalized error distribution, two computational algorithms are proposed. The first is based on indirect Bayesian inference using an approximating finite scale mixture of normal distributions. The second is based on Gibbs sampling. The Gibbs sampler involves only drawing random numbers from standard distributions. This is important because previously the impression has been that an exact analysis of the generalized error regression model using Gibbs sampling is not possible. Next, we describe computational Bayesian inference for linear models with generalized t disturbances based on Gibbs sampling, and exploiting the fact that the model is a mixture of generalized error distributions with inverse generalized gamma distributions for the scale parameter. The linear model with this specification has also been thought not to be amenable to exact Bayesian analysis. All computational methods are applied to actual data involving the exchange rates of the British pound, the French franc, and the German mark relative to the U.S. dollar.",

keywords = "Bayesian inference, Exchange rates , Generalized error distribution , Generalized t distribution , Indirect inference , Linear model , Monte Carlo methods",

author = "Michael Tsionas",

year = "2008",

doi = "10.1080/03610920701653151",

language = "English",

volume = "37",

pages = "388--407",

journal = "Communications in Statistics - Theory and Methods",

issn = "0361-0926",

publisher = "Taylor and Francis Ltd.",

number = "3",

}

RIS

TY - JOUR

T1 - Bayesian inference in generalized error and generalized student-t regression models

AU - Tsionas, Michael

PY - 2008

Y1 - 2008

N2 - This study takes up inference in linear models with generalized error and generalized t distributions. For the generalized error distribution, two computational algorithms are proposed. The first is based on indirect Bayesian inference using an approximating finite scale mixture of normal distributions. The second is based on Gibbs sampling. The Gibbs sampler involves only drawing random numbers from standard distributions. This is important because previously the impression has been that an exact analysis of the generalized error regression model using Gibbs sampling is not possible. Next, we describe computational Bayesian inference for linear models with generalized t disturbances based on Gibbs sampling, and exploiting the fact that the model is a mixture of generalized error distributions with inverse generalized gamma distributions for the scale parameter. The linear model with this specification has also been thought not to be amenable to exact Bayesian analysis. All computational methods are applied to actual data involving the exchange rates of the British pound, the French franc, and the German mark relative to the U.S. dollar.

AB - This study takes up inference in linear models with generalized error and generalized t distributions. For the generalized error distribution, two computational algorithms are proposed. The first is based on indirect Bayesian inference using an approximating finite scale mixture of normal distributions. The second is based on Gibbs sampling. The Gibbs sampler involves only drawing random numbers from standard distributions. This is important because previously the impression has been that an exact analysis of the generalized error regression model using Gibbs sampling is not possible. Next, we describe computational Bayesian inference for linear models with generalized t disturbances based on Gibbs sampling, and exploiting the fact that the model is a mixture of generalized error distributions with inverse generalized gamma distributions for the scale parameter. The linear model with this specification has also been thought not to be amenable to exact Bayesian analysis. All computational methods are applied to actual data involving the exchange rates of the British pound, the French franc, and the German mark relative to the U.S. dollar.

KW - Bayesian inference

KW - Exchange rates

KW - Generalized error distribution

KW - Generalized t distribution

KW - Indirect inference

KW - Linear model

KW - Monte Carlo methods

U2 - 10.1080/03610920701653151

DO - 10.1080/03610920701653151

M3 - Journal article

VL - 37

SP - 388

EP - 407

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 3

ER -

Research

Associated organisational unit

Links

Text available via DOI:

Keywords