Abstract

Discriminate reduction data processing is disclosed as means of providing ltivariate linear and nonlinear data reduction for the evaluation of statistically representative approximating parameters which effectively minimize parametric expressions representing sums of normalized datum variances. Weight factors are provided as products of datum error deviation coordinate normalizing proportions to account for nonlinearities, nonuniform error distributions, variable precision uncertainties. Selective data sampling is provided so as not to require certain transformation weight factor coordinate normalizing proportions. Conformal analysis is provided as an optional replacement for regression analysis to account for errors in more than a single variable parameter. Nested parameter evaluation is provided to evaluate parameters that are embedded within term functions. Applications and enhancements include provisions for general forms of curve fitting, data transformation, function approximation and corresponding forms of real time linear and nonlinear data processing. A logic control unit is configured to provide control signals to effectuate data reduction whereby a representation is provided.