Asymptotic behaviour of empirical multiinformation. (English) Zbl 0652.62005

The asymptotic behaviour of an estimator of multiinformation is investigated. It is shown that it qualitatively depends on the value of a certain numerical characteristic. If this characteristic is non-zero then the estimator is asymptotically normally distributed. In the opposite case the asymptotic distribution of the estimator is the distribution of a weighted sum of squares of independent normally distributed random variables.


62B10 Statistical aspects of information-theoretic topics
62E20 Asymptotic distribution theory in statistics
Full Text: EuDML


[1] P. Billingsley: Convergence of Probability Measures. Wiley, New York 1968. · Zbl 0172.21201
[2] W. Feller: An Introduction to Probability Theory and Its Applications. Wiley, New York 1966. · Zbl 0138.10207
[3] R. G. Galager: Information Tneory and Relaible Communication. Wiley, New York 1968.
[4] J. Gurland: Distribution of definite and of indefinite quadratic forms. Ann. Math. Statist. 26 (1955), 123-127. · Zbl 0064.12902 · doi:10.1214/aoms/1177728600
[5] Z. K. Lomicki, S. Z. Zaremba: The asymptotic distributions of estimators of the amount of transmitted information. Inform, and Control 2 (1959), 3, 260-284. · Zbl 0094.31902 · doi:10.1016/S0019-9958(59)90223-2
[6] A. Perez: \(\varepsilon\)-admissible simplifications of the dependence structure of a set of random variables. Kybemetika 13 (1977), 6, 439-449. · Zbl 0382.62003
[7] A. C. Rao: Linear Statistical Inference and Its Applications. Wiley, New York 1973. · Zbl 0256.62002
[8] J. Zvárová: The asymptotic distribution of sample information measure of dependence (in Czech). Kybemetika 5 (1969), 1, 50-59.
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.