发帖
雷达卡
【原刊地名】京
【原刊期号】20101
【原刊页号】151～160
【分 类 号】F104
【分 类 名】统计与精算
【复印期号】201003
【英文标题】A Study on the Nonparametric Estimation Method of Nonlinear Econometric Model
【作 者】马薇/袁铭
【作者简介】马薇，袁铭，天津财经大学。
【内容提要】本文提出使用核估计的方法构造平滑转移模型(STR)的非参数模拟最大似然估计(NPSML)，给出了NPSML估计量的构造方法、渐近性质以及相应的核函数和窗宽的选择准则，并利用滑动窗宽算法对估计量的构造过程进行了改进。通过Monte Carlo实验证明，该方法是可靠的，并且当误差项存在序列相关时，此种估计量是稳健的。
【摘 要 题】理论与方法
【英文摘要】This paper proposes nonparametric simulated maximum likelihood (NPSML) estimation for smooth transition model by kernel method. We provide a unified framework for constructing NPSML estimator and give rules for the choice of kernel function and bandwidth, and then use a slide variable bandwidth algorithm to improve its accuracy and reliability. Monte Carlo simulation study shows NPSML estimator is consistent and asymptotically efficient and robust when the error terms represent serial correlation.
【关 键 词】平滑转移模型/非参数模拟最大似然估计/滑动窗宽算法
smooth transition model/NPSML/slide variable bandwidth algorithm
【正 文】
...............
【参考文献】
[1]刘金全、李庆华、郑挺国：《具有平滑迁移的ARFIMA模型及其应用》[J]，《中国管理科学》2007年第6期。
[2]Amado, C. and Ters virta, T. Modeling Conditional and Unconditional Heteroskedasticity with Smoothly Time-varying Structure[R], Working Paper. 2008.
[3]Areasa, McAleer. Moment-based Estimation of Smooth Transition Regression Models with Endogenous Variables[R], Working Paper. 2008, 36.
[4]Fermanian, J.-D. and B. Salanié. A Nonparametric Simulated Maximum Likelihood Estimation Method[J], Econometric Theory, 2004,20:701～734.
[5]P tscher B.M. and I.V. Prucha. Dynamic Nonlinear Econometric Models-Asymptotic Theory[M], Berlin: Springer-Vetlag. 1997.
[6]Rothman, van Dijk and Franses. A Multivariate STAR Analysis of the Relationship between Money and Output[J], Macroeconomic Dynamics, 2001,5:506～532.
[7]Ter isvirta, T. Specification, Estimation, and Evaluation of Smooth Transition Autoregressive Models[J], Journal of the American Statistical Association. 1994,89:208～218.
[8]Ters virta. Modelling Nonlinear Economic Time Series[M], 2008.
[9]Dimitrios D. Thomakos. A Semiparametric Smooth Transition ARX Model for Nonlinear Time Series[R], Working Paper. 2003.
[10]Timo Terasvirta, Dick van Dijk. Panel Smooth Transition Regression Models[J], SSEPEFI Working Paper Series in Economics and Finance. No. 6041.
[11]Wooldridge, J.M. Estimation and Inference for Dependent Processes[C], in R.F. Engle and D.L. McFadden(eds.), Handbook of Econometrics[A], 2004.Vol. IV, Amsterdam: Elsevier Science, 2639～2738.
京公网安备 11010802022788号
