Comparison of Methods for Probabilistic Uncertainty Bounding
1999 (English)In: Proceedings of the 38th IEEE Conference on Decision and Control, 1999, 522-527 vol.1 p.Conference paper (Refereed)
The problem of computing probabilistic uncertainty regions for the frequency responses of identified models is studied. A novel method for uncertainty bounding that uses bootstrap is presented and compared to a classical method using estimated covariance information. It is shown that, with bootstrap, it is possible to compute realistic uncertainty regions that closely resemble those obtainable through Monte Carlo simulations.
Place, publisher, year, edition, pages
1999. 522-527 vol.1 p.
Model uncertainty, Identification, Bootstrap
IdentifiersURN: urn:nbn:se:liu:diva-94081DOI: 10.1109/CDC.1999.832835ISBN: 0-7803-5250-5OAI: oai:DiVA.org:liu-94081DiVA: diva2:629107
38th IEEE Conference on Decision and Control, Phoenix, AZ, USA, December, 1999