Sign in
Stochastic and worst case system identification are not necessarily incompatible
Journal article   Peer reviewed

Stochastic and worst case system identification are not necessarily incompatible

Er-Wei Bai and Mark S Andersland
Automatica (Oxford), Vol.30(9), pp.1491-1493
09/1994
DOI: 10.1016/0005-1098(94)90017-5

View Online

Abstract

Stochastic and worst case approaches to system identification are different and are usually treated separately. In this communique we investigate the effect that a projection operator has on the worst case behavior of estimates derived by stochastic identification algorithms. We show that under certain assumptions the projections of the stochastic estimates are convergent in the worst case setting. We illustrate this result by applying it to least squares and maximum likelihood algorithms.
estimation parameter estimation identification System identification least squares estimation

Details

Metrics