Bayesian inference for the Errors-In-Variables model

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Wuhan University
  • The Ohio State University
  • Tongji University
View graph of relations

Details

Original languageEnglish
Pages (from-to)35-52
Number of pages18
JournalStudia geophysica et geodaetica
Volume61
Issue number1
Early online date9 Aug 2016
Publication statusPublished - Jan 2017

Abstract

We discuss the Bayesian inference based on the Errors-In-Variables (EIV) model. The proposed estimators are developed not only for the unknown parameters but also for the variance factor with or without prior information. The proposed Total Least-Squares (TLS) estimators of the unknown parameter are deemed as the quasi Least-Squares (LS) and quasi maximum a posterior (MAP) solution. In addition, the variance factor of the EIV model is proven to be always smaller than the variance factor of the traditional linear model. A numerical example demonstrates the performance of the proposed solutions.

Keywords

    Bayesian inference, Errors-In-Variables, Maximum Likelihood, Total Least-Squares, informative prior, noninformative prior, quasi solution

ASJC Scopus subject areas

Cite this

Bayesian inference for the Errors-In-Variables model. / Fang, Xing; Li, Bofeng; Alkhatib, Hamza et al.
In: Studia geophysica et geodaetica, Vol. 61, No. 1, 01.2017, p. 35-52.

Research output: Contribution to journalArticleResearchpeer review

Fang X, Li B, Alkhatib H, Zeng W, Yao Y. Bayesian inference for the Errors-In-Variables model. Studia geophysica et geodaetica. 2017 Jan;61(1):35-52. Epub 2016 Aug 9. doi: 10.1007/s11200-015-6107-9
Fang, Xing ; Li, Bofeng ; Alkhatib, Hamza et al. / Bayesian inference for the Errors-In-Variables model. In: Studia geophysica et geodaetica. 2017 ; Vol. 61, No. 1. pp. 35-52.
Download
@article{f4139c125c9a449d8ffa56a80fed182f,
title = "Bayesian inference for the Errors-In-Variables model",
abstract = "We discuss the Bayesian inference based on the Errors-In-Variables (EIV) model. The proposed estimators are developed not only for the unknown parameters but also for the variance factor with or without prior information. The proposed Total Least-Squares (TLS) estimators of the unknown parameter are deemed as the quasi Least-Squares (LS) and quasi maximum a posterior (MAP) solution. In addition, the variance factor of the EIV model is proven to be always smaller than the variance factor of the traditional linear model. A numerical example demonstrates the performance of the proposed solutions.",
keywords = "Bayesian inference, Errors-In-Variables, Maximum Likelihood, Total Least-Squares, informative prior, noninformative prior, quasi solution",
author = "Xing Fang and Bofeng Li and Hamza Alkhatib and Wenxian Zeng and Yibin Yao",
year = "2017",
month = jan,
doi = "10.1007/s11200-015-6107-9",
language = "English",
volume = "61",
pages = "35--52",
journal = "Studia geophysica et geodaetica",
issn = "0039-3169",
publisher = "Springer Netherlands",
number = "1",

}

Download

TY - JOUR

T1 - Bayesian inference for the Errors-In-Variables model

AU - Fang, Xing

AU - Li, Bofeng

AU - Alkhatib, Hamza

AU - Zeng, Wenxian

AU - Yao, Yibin

PY - 2017/1

Y1 - 2017/1

N2 - We discuss the Bayesian inference based on the Errors-In-Variables (EIV) model. The proposed estimators are developed not only for the unknown parameters but also for the variance factor with or without prior information. The proposed Total Least-Squares (TLS) estimators of the unknown parameter are deemed as the quasi Least-Squares (LS) and quasi maximum a posterior (MAP) solution. In addition, the variance factor of the EIV model is proven to be always smaller than the variance factor of the traditional linear model. A numerical example demonstrates the performance of the proposed solutions.

AB - We discuss the Bayesian inference based on the Errors-In-Variables (EIV) model. The proposed estimators are developed not only for the unknown parameters but also for the variance factor with or without prior information. The proposed Total Least-Squares (TLS) estimators of the unknown parameter are deemed as the quasi Least-Squares (LS) and quasi maximum a posterior (MAP) solution. In addition, the variance factor of the EIV model is proven to be always smaller than the variance factor of the traditional linear model. A numerical example demonstrates the performance of the proposed solutions.

KW - Bayesian inference

KW - Errors-In-Variables

KW - Maximum Likelihood

KW - Total Least-Squares

KW - informative prior

KW - noninformative prior

KW - quasi solution

UR - http://www.scopus.com/inward/record.url?scp=84981290356&partnerID=8YFLogxK

U2 - 10.1007/s11200-015-6107-9

DO - 10.1007/s11200-015-6107-9

M3 - Article

VL - 61

SP - 35

EP - 52

JO - Studia geophysica et geodaetica

JF - Studia geophysica et geodaetica

SN - 0039-3169

IS - 1

ER -

By the same author(s)