We consider the problem of parameter estimation in a linear stochastic model, where the observations are affected by noise with uncertain variance. In particular, we discuss a linear estimator which minimizes a worst-case measure of the a-posteriori covariance of the parameters. The estimate is efficiently computed by means of convex programming, and may be updated with upcoming observations in a recursive setting
Minimum Variance Estimation with Uncertain Statistical Model / CALAFIORE G.C.; EL GHAOUI L.. - STAMPA. - 4(2001), pp. 3497-3499. ((Intervento presentato al convegno 40th Conference on Decision and Control tenutosi a Orlando, FL nel 04-07 Dec 2001.
Titolo: | Minimum Variance Estimation with Uncertain Statistical Model |
Autori: | |
Data di pubblicazione: | 2001 |
Abstract: | We consider the problem of parameter estimation in a linear stochastic model, where the observati...ons are affected by noise with uncertain variance. In particular, we discuss a linear estimator which minimizes a worst-case measure of the a-posteriori covariance of the parameters. The estimate is efficiently computed by means of convex programming, and may be updated with upcoming observations in a recursive setting |
ISBN: | 0780370619 |
Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
http://hdl.handle.net/11583/1408962