Asymptotic Properties of the most Generalized Optimal Stochastic Approximation Procedures

Abstract

In this paper we consider the most general nonlinear regression model, Y(x)=ψ(θ_((1) ) ) g_1 (θ_((2) );x)+ε , prove of the almost sure convergence, and asymptotic normality of the estimators for the nonlinear parameters, using the most general optimal stochastic approximation procedure. A procedure for constructing the general confidence intervals for the vector of nonlinear parameters is also developed; the most generalized nonlinear regression model is introduced. We establish asymptotic properties for the most generalized model.