Statistics and Its Interface

Volume 7 (2014)

Number 4

Special Issue on Modern Bayesian Statistics (Part I)

Guest Editor: Ming-Hui Chen (University of Connecticut)

Fully probabilistic knowledge expression and incorporation

Pages: 503 – 515

DOI: http://dx.doi.org/10.4310/SII.2014.v7.n4.a7

Authors

Miroslav Kárný (UTIA AVCR, Prague, Czech Republic)

Tatiana V. Guy (UTIA AVCR, Prague, Czech Republic)

Jan Kracík (Department of Applied Mathematics, VSB-Technical University of Ostrava, Czech Republic)

Petr Nedoma (UTIA AVCR, Prague, Czech Republic)

Antonella Bodini (CNR IMATI, Milano, Italy)

Fabrizio Ruggeri (CNR IMATI, Milano, Italy)

Abstract

An exploitation of prior knowledge in parameter estimation becomes vital whenever measured data is not informative enough. Elicitation of quantified prior knowledge is a well-elaborated art in societal and medical applications but not in the engineering ones. Frequently required involvement of a facilitator is mostly unrealistic due to either facilitator’s high costs or complexity of modelled relationships that cannot be grasped by humans. This paper provides a facilitator-free approach based on an advanced knowledge-sharing methodology. It presents the approach on commonly available types of knowledge and applies the methodology to a normal controlled autoregressive model.

Keywords

Bayesian estimation, automatised knowledge elicitation, just-in-time modelling, controlled autoregressive model

2010 Mathematics Subject Classification

Primary 62C10, 62F15. Secondary 62M10.

Full Text (PDF format)