Erscheint 12 Ausgaben pro Jahr
ISSN Druckformat: 1064-2315
ISSN Online: 2163-9337
Indexed in
Investigation of Consistency of Estimates of Parameters of the Gibbs Distribution Obtained by the Least Square Method
ABSTRAKT
Conditions of strong consistency of least square estimate for Markovian sequences with the Gibbs distribution were considered. We stated and proved theorems, which make it possible to approximate criterion function of Markovian process with unique point of maximum by its empiric estimate. In spite of their theoretical character the obtained results have sufficiently wide sphere of practical application on stochastic processes modeling.
-
Winkler G., Analysis, random fields and dynamic Monte Carlo methods.
-
Besag J.E. , Spatial interaction and the statistical analysis of lattice systems.
-
Samosonok A.S., Asymptotic properties of estimate of maximal plausibility for the Gibbs fields.
-
Gikhman I.I., Skorokhod A.V., Theory of random processes.
-
Dorogovtsev A.Ya., On a statement useful on proof of estimates consistency.
-
Knopov P.S., Optimal estimates of parameters of stochastic systems.
-
Korolyuk V.S., Portenko N.I., Skorokhod A.V., Turbin A.F., Handbook on probability theory and mathematical statistics.