Identification by the recurrent method of least squares when the conditions of the Gauss-Markov theorem are not satisfied. (English. Russian original) Zbl 0842.93079
J. Comput. Syst. Sci. Int. 33, No. 2, 8-14 (1995); translation from Izv. Ross. Akad. Nauk, Tekh. Kibern. 1993, No. 4, 29-34 (1993).
The authors consider an identification problem when the conditions of the Gauss-Markov theorem are not satisfied. The estimate is projected onto an identification subspace where the information matrix increases to verify consistency.
Reviewer: T.Duncan (Lawrence)
MSC:
93E12 | Identification in stochastic control theory |
93E24 | Least squares and related methods for stochastic control systems |