A New Nonlinear Multiregression Model Based on the Lower and Upper Integrals

Abstract

A new nonlinear multiregression model based on a pair of extreme nonlinear integrals, lower and upper integrals, is established in this paper. A complete data set of predictive attributes and the relevant objective attribute is required for estimating the regression coefficients. Due to the nonadditivity of the model, a genetic algorithm combined with the pseudo gradient search is adopted to search the optimized solution in the regression problem. Applying such a nonlinear multiregression model, an interval prediction for the value of the objective attribute can be made once a new observation of predictive attributes is available.