Hierarchical Bayesian approaches for robust inference in ARX models
2012 (English)In: Proceedings from the 16th IFAC Symposium on System Identification, 2012 / [ed] Michel Kinnaert, International Federation of Automatic Control , 2012, Vol. 16 Part 1, 131-136 p.Conference paper, Presentation (Refereed)
Gaussian innovations are the typical choice in most ARX models but using other distributions such as the Student's t could be useful. We demonstrate that this choice of distribution for the innovations provides an increased robustness to data anomalies, such as outliers and missing observations. We consider these models in a Bayesian setting and perform inference using numerical procedures based on Markov Chain Monte Carlo methods. These models include automatic order determination by two alternative methods, based on a parametric model order and a sparseness prior, respectively. The methods and the advantage of our choice of innovations are illustrated in three numerical studies using both simulated data and real EEG data.
Place, publisher, year, edition, pages
International Federation of Automatic Control , 2012. Vol. 16 Part 1, 131-136 p.
, IFAC papers online, ISSN 1474-6670 ; 2012
Particle Filtering/Monte Carlo Methods; Bayesian Methods
IdentifiersURN: urn:nbn:se:liu:diva-81258DOI: 10.3182/20120711-3-BE-2027.00318ISBN: 978-3-902823-06-9OAI: oai:DiVA.org:liu-81258DiVA: diva2:551244
The 16th IFAC Symposium on System Identification, July 11-13, Brussels, Belgium
FunderSwedish Research Council