基于面板数据均值变点的气象数据统计分析

Statistical Analysis of Meteorological Data Based on Mean Change Point of Panel Data

气候变化是全球公认的环境困境,研究气象序列的变结构对预防自然灾害有重要意义。本文基于面板数据对气象数据序列进行变点研究,采用一个比率型检验统计量来检验序列中是否存在共同变点,利用bootstrap方法计算检验统计量的临界值。实证分析了2018年合肥的肥东、肥西、巢湖、长丰、庐江和合肥市区6个台站的日平均气温序列的均值共同变点问题,区分识别气候因素变点与非气候因素变点,进而找出气象序列结构性变化的真正原因。

It is recognized that climate change is a global environmental dilemma.Studying the variable structure of meteorological sequences is important for preventing natural disasters.Based on panel data,the change point of the meteorological sequences is studied in this paper.A ratio test statistic is used to test whether there is a common change point in the sequence,and the critical value of the test statistic is calculated by the bootstrap method.Finally,the common change points of the average daily temperature series of 6 stations in Hefei’s Feidong,Feixi,Chaohu,Changfeng,Lujiang,and Hefei urban areas in 2018 are detected,and the change points of climatic factors and non-climatic factors are identified.The real reasons for the structural changes of the meteorological sequence are found in this paper.