基于ASAMC算法的气象数据多变点估计  

Multiple change-point estimation for meteorological data based on ASAMC algorithm

作　　者：许欢[1] 谭常春[1] 

机构地区：[1]合肥工业大学数学学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2016年第12期1719-1723,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(11201108);全国统计科研计划重点资助项目(2012LZ009);中央高校基本科研业务费专项资金资助项目(JZ2015HGXJ0177)

摘　　要：文章主要研究了安徽省某气象台站年平均气温、月平均气温的结构性变化情况。该文在对气温数据进行正态性检验的基础上,运用ASAMC(annealing stochastic approximation Monte Carlo)算法对气温数据进行统计分析,估计出平均气温结构性变化的位置,并探索发生结构性变化的气象因素和非气象因素。In this paper, the investigation on structural changes of annual and monthly mean tempera- ture based on the statistics of a meteorological station in Anhui Province is conducted. Firstly, the normality test of temperature statistics is conducted. Then the temperature data is analyzed by using the annealing stochastic approximation Monte Carlo（ASAMC） algorithm, and the structural changes of mean temperature are estimated. The meteorological and non-meteorological factors leading to the structural changes are also explored by this method.

关 键 词：ASAMC算法 Bayes多变点模型 M-H算法 平均气温 

分 类 号：O212.7[理学—概率论与数理统计]