The problem of constructing sequential estimates of the parameters of recursion processes when there are independent noises is solved. It is shown that sequential estimates have the property of uniform boundedness of the mean-square deviation. As an example, the problem of estimating the parameters of an autoregressive process from noisy observations is examined. It is shown that, if the process is stable, then its parameters can be estimated with a given accuracy.
|Number of pages||10|
|Publication status||Published - Nov 1982|
ASJC Scopus subject areas