Scientific journal

ISSN 1814-2400

INFORMATION SCIENCE AND CONTROL SYSTEMS

Lapko A. V., Lapko V. A.

NONPARAMETRIC COLLECTIVE OF LINEAR APPROXIMATIONS IN THE PROBLEM OF RECONSTRUCTING STOCHASTIC DEPENDENCIES

We consider a technique for constructing a nonparametric collective in the problem of restoring stochastic dependencies, which ensures the effective calculation of a priori information of the initial statistical data. The structure of the non-parametric collective and its properties are analyzed.

Keywords: nonparametric regression, linear approximations, collective of decision functions, asymptotic properties