Abstract:

An approach for constructing nonparametric imprecise growth models (regression models) is proposed. The approach is based on applying sets of probability distributions of the "noise" produced by means of Kolmogorov-Smirnov bounds. The corresponding growth models are constructed by minimizing the risk functional in the framework of predictive learning and by choosing "optimal" probability distribuions of the "noise" defining the minimax and minimin strategies. Numerical examples illustrate the proposed approach.
Received on March 16, 2009, revised on June 22, 2010
References: 16