Theory of Probability and Mathematical Statistics
Multivariate statistical experiments with persistent non-linear regression and equilibrium
D. V. Koroliouk
Download PDF
Abstract: A sequence of multivariate statistical experiments with persistent non-linear regression is considered. This sequence is determined by a matrix of directing actions for frequencies of certain attributes. Conditions for the convergence of multivariate statistical experiments to a state of equilibrium are studied. A stochastic approximation by an autoregressive process with normal perturbations is constructed for the discrete time model.
Keywords: Multivariate statistical experiments, regression function, equilibrium, stochastic approximation
Bibliography: 1. D. V. Koroliouk, Binary repeating statistical experiments with persistent linear regression, Ukr. Matem. Vestnik 10 (2013), no. 4, 497-506. (Russian)
2. D. V. Koroliouk, Two component binary statistical experiments with persistent linear regression, Teor. Ĭmovir. Mat. Stat. 90 (2014), 91-101; English transl. in Theor. Probability and Math. Statist. 90 (2015), 103-114.
3. M. B. Nevel'son and R. Z. Has'minskiĭ, Stochastic Approximation and Recursive Estimation, ''Nauka'', Moscow, 1972; English transl., American Mathematical Society, Providence, 1973.
4. D. S. Pupashenko, S. V. Shklyar, and A. G. Kukush, Asymptotic properties of corrected score estimator in autoregressive model with measurement errors, Teor. Ĭmovir. Mat. Stat. 89 (2013), 156-166; English transl. in Theory Probab. Math. Statist. 89 (2014), 169-180.
5. Stewart N. Ethier and Thomas G. Kurtz, Markov Processes: Characterization and Convergence, Wiley Series in Probability and Mathematical Statistics: Probability and Mathematical Statistics, John Wiley & Sons, Inc., New York, 1986.
6. Yu. V. Borovskikh and V. S. Koroliyuk, Martingale Approximation, VSP, Utrecht, 1997.
