Using simulation to compare between parametric and nonparametric transfer function model

Abstract

ABSTRACTIn this paper, The transfer function model in the time series was estimated using different methods, including parametric Represented by the method of the Conditional Likelihood Function, as well as the use of abilities nonparametric are in two methods local linear regression and cubic smoothing spline method, This research aims to compare those capabilities with the nonlinear transfer function model by using the style of simulation and the study of two models as output variable and one model as input variable in addition to generating random error in the model of the transfer function model that follows the ARMA model by two functions and a variation (0.5) at sample sizes (n = 100,150,200) The results showed the superiority of the nonparametric transfer function model at the cubic smoothing spline estimator C.S.S On the nonlinear and nonparametric transfer function model.