zbMATH — the first resource for mathematics

Estimation of jumplike processes with incomplete information. (English. Russian original) Zbl 0541.93062
Autom. Remote Control 44, 1438-1443 (1983); translation from Avtom. Telemekh. 1983, No. 11, 64-71 (1983).
Summary: An estimation method is proposed for the instants of jumplike variation of the parameters of a random process in the absence of information about the probability characteristics of the variations; only one of the states of the parameter variation process is known. The example of an autoregression model is used for studying this procedure and comparing it with optimal methods constructed under conditions of full information.
93E10 Estimation and detection in stochastic control theory
60J75 Jump processes (MSC2010)
93E25 Computational methods in stochastic control (MSC2010)
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)