成分数据路径分析模型  

Path Modeling for Compositional Data

作　　者：夏棒 王惠文[2,3] 周荣刚[2,3] XIA Bang;WANG Hui-wen;ZHOU Rong-gang(Postdoctoral Workstation, Industrial and Commercial Bank of China, Beijing 100032, China;School of Economics and Management, Beihang University, Beijing 100191, China;Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing 100191,China)

机构地区：[1]中国工商银行博士后科研工作站,北京100032 [2]北京航空航天大学经济管理学院,北京100191 [3]北京航空航天大学大数据科学与脑机智能高精尖创新中心,北京100191

出　　处：《数学的实践与认识》2019年第14期191-199,共9页Mathematics in Practice and Theory

基　　金：国家自然科学基金(71420107025; 71640034)

摘　　要：路径分析是一种探索和验证系统内部各个因素之间因果关系的多元统计方法.本文针对现实中大量存在的成分数据变量,提出成分数据路径分析模型,给出模型的方程表达形式和图形表达形式.在成分数据多元线性回归的基础上,提出模型的参数估计方法,并利用Bootstrap分析技术,给出路径系数显著性检验办法.在某公司官方网站的用户满意度与推荐意愿影响因素应用研究中,成分数据路径分析建模结果表明,满意度主要受到易用性的影响,而推荐意愿主要受到有用性的影响.这一结论为网站原型设计与营销推广提供了新的启示.Path analysis is a multivariate statistical method for exploring and verifying the causal relationship among the various factors in a system.In this paper,for the existence of large amount of compositional data variables in reality,a path model for compositional data is proposed,and the expression forms of the equation and graphics of the model are given.Based on the multivariate linear regression of compositional data,the parameter estimation method of the model is proposed,and Bootstrap technique is used to test the significance of the model parameters.In the research on user satisfaction and recommendation intention of the official website of one mobile company,application results using path model for compositional data show that user satisfaction is mainly determined by ease of use while recommendation intention is strongly influenced by usefulness.This conclusion provides new references for the prototyping and marketing promotion of a website.

关 键 词：成分数据 最小二乘 路径分析 满意度 

分 类 号：O212.4[理学—概率论与数理统计]