Abstract
The principal object of the investigation is a family of scalar products defined on a Hilbert space ℋ. For this general case of the theory of linear statistical inference, we obtain a counterpart of the Neyman-Fisher factorization theorem, and we introduce and study counterparts of the Fisher information and of the information matrix that preserve all the important properties of their classical prototypes. By additionally introducing the concept of observation interpreted as a linear functional on ℋ that satisfies a certain additional condition, we can construct a natural counterpart of the maximum likelihood method.
Similar content being viewed by others
Literature cited
O. V. Gerlein (Gerleyn) and A. M. Kagan, “Contributions to the theory of linear statistical inference,” Proceedings of the IASPS Symposium to honor Prof. J. Neyman, Warsaw (1974).
A. M. Kagan, “The Fisher information contained in a finite-dimensional linear space, and a correct version of the method of moments,” Probl. Peredachi Inf. (1975).
R. R. Bahadur, “Sufficiency and statistical decision functions,” Ann. Math. Stat.,25, 3, 423–462 (1954).
P. Halmos and L. Savage, “Application of the Radon-Nikodym theorem to the theory of sufficient statistics,” Ann. Math. Stat.,20, 2, 225–241 (1949).
F. Riesz and B. Szökefalvi-Nagy, Lectures on Functional Analysis, Akademiai Kiado, Budapest (1953).
H. Cramer, Mathematical Methods of Statistics, Princeton Univ. Press, Princeton, New Jersey (1946).
C. R. Rao, “Information and accuracy attainable in estimation of statistical parameters,” Bull. Calcutta Math. Soc.,37, 1, 81–91 (1945).
D. Blackwell, “Conditional expectation and unbiased sequential estimation,” Ann. Math. Stat.,18, 1, 105–110 (1947).
H. Cramer, “Contributions to the theory of statistical estimation,” Scand. Aktuar.,18, 1, 85–94 (1946).
A. Bhattacharya, “On some analogues to the amount of information and their uses in statistical estimation,” Sankhya,8, 1, 1–14 (1946).
Laurent Schwartz, Analysis, Vol. 1 [Russian translation], Moscow (1972).
V. P. Godambe, “An optimum property of regular maximum likelihood estimation,” Ann. Math. Stat.,31, 4 (1960).
O. V. Shalaevskii, “Short proof of Cramer-Rao inequality,” Teor. Verovatn. Ee Primen.,6, 3, 352–353 (1961).
L. N. Bol'shev, “Sharpened Cramer-Rao inequality,” Teor. Veroyatn. Ee Primen.,6, 3, 319–326 (1961).
N. I. Akhiezer and I. M. Glazman, Theory of Linear Operators in Hilbert Space, Ungar Press.
Additional information
Translated from Zapiski Nauchnykh Seminarov Leningradskogo Otdeleniya Matematicheskogo Instituta im. V. A. Steklova AN SSSR, Vol. 53, pp. 64–100, 1975.
Rights and permissions
About this article
Cite this article
Gerlein, O.V., Kagan, A.M. Hilbert space methods in classical problems of mathematical statistics. J Math Sci 12, 184–213 (1979). https://doi.org/10.1007/BF01262718
Issue Date:
DOI: https://doi.org/10.1007/BF01262718