欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
面板数据的有序聚类分析是多元统计分析的新兴研究领域。借鉴多元统计学中主成分分析方法对面板数据在时间变量上进行降维处理，把变异信息的损失降低到最小，较为准确地反映了样本在各时间段内的整体变化水平；采用费希尔最优求解算法对主成分得分进行有序聚类，为研究有序面板数据的亲疏关系提供一些思路；对全球气候变化进行聚类分析，分析五十年来全球及区域气候变化特点，与国外研究结论对比，显示出良好的应用性。
英文摘要：
The ordered clustering analysis of panel data is a new research field of multivariate statistical analysis. This paper reduces dimension of panel data by means of principal component analysis, minimizes the loss of variant information to a minimum, accurately reflects overall change level of samples in the different period, then uses fisher optimal dissection method to conduct the ordered clustering analysis into the score of principal component and puts forward the effective research approaches on panel data＇s affinities. After that the authors use this algorithm to analysis the global climate change, analysis the characteristics of global and regional climate change in past 50 years. The method is proved to be effective through the comparison of the research and foreign studies.
同期刊论文项目
同项目期刊论文
The Dynamic Fluctuation Relationship between China’s Urbanization and the Disparity of Urban-Rural R
期刊信息
位置：