AR模型阶数的强相合估计  

Strong Consistent Estimation of Order for AR Model

作　　者：彭家龙[1] 吴宏锷[2] 刘次华[3] 

机构地区：[1]西安建筑科技大学理学院,陕西西安710055 [2]南阳理工学院应用数学系,河南南阳473000 [3]华中科技大学数学系,湖北武汉430074

出　　处：《昆明理工大学学报（理工版）》2009年第3期117-120,124,共5页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助(项目编号:10301011)

摘　　要：引入贝叶斯因子来判定AR模型的阶数,给出AR模型阶数k的一个强相合估计,最后用随机模拟对其与AIC(k),BIC(k)两种定阶准则进行比较得出,该估计量的判别效果优于AIC(k)准则.In this paper, we discuss the problem of determining the order of AR model based on Bayes factor. A strong consistent estimation of the order of AR model is given. Finally, stochastic simulation is used to compare the estimation with that of using AIC, BIC criterion. It is shown through the results that it is better than the AIC criterion.

关 键 词：模型 阶数的估计 贝叶斯因子 强相合性 

分 类 号：O211.61[理学—概率论与数理统计]