×

Divergences of Gauss-Markov random fields with application to statistical inference. (English) Zbl 0664.62086

In addition to the previous asymptotic theory of parameter estimation [cf. the author, ibid. 24, No.3, 161-176 (1988; Zbl 0655.62094)] further asymptotic properties of Gauss-Markov random fields are studied in the present paper. Explicit formulas for the entropy rate, the I- divergence,and the \(\alpha\)-divergence are obtained. Applications to parameter estimation and hypotheses testing are included.

MSC:

62M05 Markov processes: estimation; hidden Markov models
62M99 Inference from stochastic processes
62F12 Asymptotic properties of parametric estimators
60G60 Random fields
62F03 Parametric hypothesis testing

Citations:

Zbl 0655.62094
PDFBibTeX XMLCite
Full Text: EuDML Link

References:

[1] R. L. Dobrushin: Gaussian random fields – Gibbsian point of view. Multicomponent random systems (R. L. Dobrushin, Ya. G. Sinai. M. Dekker, New York 1980, 119-151. · Zbl 0499.60046
[2] M. Janžura: Asymptotic theory of parameter estimation for Gauss-Markov random fields. Kybernetika 24 (1988) 3, 161-176. · Zbl 0655.62094
[3] H. Künsch: Thermodynamics and statistical analysis of Gaussian random fields. Z. Wahrsch. verw. Gebiete 58 (1981), 407-421. · Zbl 0458.60053
[4] C. Preston: Random Fields. (Lecture Notes in Mathematics 534.) Springer-Verlag, Berlin–Heidelberg–New York 1976. · Zbl 0335.60074 · doi:10.1007/BFb0080563
[5] E. M. Stein, G. Weiss: Introduction to Fourier Analysis on Euclidean Spaces. Princeton University Press, Princeton, N. J. 1971. · Zbl 0232.42007
[6] I. Vajda: A new general approach to minimum distance estimation. Trans. Ninth Prague Conference on Inform. Theory, Statist. Dec. Functions, Random Processes. Academia, Prague 1983, 103-112. · Zbl 0552.62016
[7] I. Vajda: Efficiency and robustness control via distorted maximum likelihood estimation. Kybernetika 22 (1986), 47-67. · Zbl 0603.62039
[8] I. Vajda: Theory of Statistical Inference and Information. Reidel, Amsterdam 1988.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.