| 不同类型识别变量的自回归模型异常值探测的Bayes方法 |
| |
| 引用本文： | 张倩倩,归庆明,王延停.不同类型识别变量的自回归模型异常值探测的Bayes方法[J].测绘学报,2012,41(3):378-384. |
| |
| 作者姓名： | 张倩倩 归庆明 王延停 |
| |
| 作者单位： | 1. 信息工程大学理学院,河南郑州,450001
2. 信息工程大学理学院,河南郑州450001／信息工程大学测绘学院,河南郑州450052 |
| |
| 基金项目： | 国家自然科学基金，中国卫星导航学术年会青年优秀论文获奖者资助课题，郑州市科技计划攻关项目 |
| |
| 摘 要： | 讨论基于自回归模型(AR模型)的时间序列数据中异常值探测的Bayes方法。该方法针对自回归模型引入不同类型的识别变量,通过比较这些识别变量的后验概率值与事先给定的阈值来进行异常值定位;基于Gibbs抽样算法,提出识别变量后验概率值的计算方法和异常值的估算方法;进行了大量的模拟试验并把该方法应用于卫星钟差实测数据的异常值探测,结果表明,该方法对于解决时间序列数据中在同一时刻或不同时刻出现加性异常值或革新异常值的探测问题是可行的和有效的。
|
| 关 键 词： | 自回归模型 加性异常值 革新异常值 识别变量 Bayes方法 Gibbs抽样 卫星钟差 |
Bayesian Methods for Outliers Detection in Autoregressive Model Based on Different Types of Classification Variables |
| |
| ZHANG Qianqian,GUI Qingming,WANG Yanting.Bayesian Methods for Outliers Detection in Autoregressive Model Based on Different Types of Classification Variables[J].Acta Geodaetica et Cartographica Sinica,2012,41(3):378-384. |
| |
| Authors: | ZHANG Qianqian GUI Qingming WANG Yanting |
| |
| Institution: | 1.Institute of Science,Information Engineering University,Zhengzhou 450001,China;2.Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450052,China |
| |
| Abstract: | A Bayesian procedure for outlier detection in time series is discussed.The main idea of this method is introducing different types of classification variables into autoregressive model.Then outliers can be detected by comparing the posterior probabilities of these classification variables with a given threshold.Besides,a procedure for computing the posterior probabilities of classification variables and obtaining the estimates of outliers is designed based on Gibbs sampling.A large number of simulation experiments and an experiment of real clock error data are carried out.It is shown that the new procedure is applicable to detect additive and innovational outliers occurring at the same time or not in time series. |
| |
| Keywords: | AR model additive outlier innovation outlier classification variable Bayesian method Gibbssampling satellite clock error |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
