In this paper,we improve the algorithm proposed by T.F.Colemen and A.R.Conn in paper [1]. It is shown that the improved algorithm is possessed of global convergence and under some conditions it can obtain locally supp...In this paper,we improve the algorithm proposed by T.F.Colemen and A.R.Conn in paper [1]. It is shown that the improved algorithm is possessed of global convergence and under some conditions it can obtain locally supperlinear convergence which is not possessed by the original algorithm.展开更多
In this paper, the optimal convergence rates of estimators based on kernel approach for nonlinear AR model are investigated in the sense of Stone[17,18]. By combining the or mixingproperty of the stationary solution w...In this paper, the optimal convergence rates of estimators based on kernel approach for nonlinear AR model are investigated in the sense of Stone[17,18]. By combining the or mixingproperty of the stationary solution with the characteristics of the model itself, the restrictiveconditions in the literature which are not easy to be satisfied by the nonlinear AR model areremoved, and the mild conditions are obtained to guarantee the optimal rates of the estimatorof autoregression function. In addition, the strongly consistent estimator of the variance ofwhite noise is also constructed.展开更多
文摘In this paper,we improve the algorithm proposed by T.F.Colemen and A.R.Conn in paper [1]. It is shown that the improved algorithm is possessed of global convergence and under some conditions it can obtain locally supperlinear convergence which is not possessed by the original algorithm.
文摘In this paper, the optimal convergence rates of estimators based on kernel approach for nonlinear AR model are investigated in the sense of Stone[17,18]. By combining the or mixingproperty of the stationary solution with the characteristics of the model itself, the restrictiveconditions in the literature which are not easy to be satisfied by the nonlinear AR model areremoved, and the mild conditions are obtained to guarantee the optimal rates of the estimatorof autoregression function. In addition, the strongly consistent estimator of the variance ofwhite noise is also constructed.