隐变量交互作用分析建模及其在SAS上的实现  

Modeling Latent Variable Interaction Effect Analysis and Its Realization by SAS Software

作　　者：李建明[1] 曲成毅[2] 

机构地区：[1]山西医科大学数学教研室,太原030001 [2]山西医科大学流行病学教研室,太原030001

出　　处：《数学的实践与认识》2007年第1期31-37,共7页Mathematics in Practice and Theory

基　　金：国家自然基金(30571611)

摘　　要：探讨隐变量交互作用分析的建模方法及其在SA S软件上的实现;首先阐述隐变量交互作用分析建模的原理,通过拟合一个隐变量交互作用分析示例,对加入交互作用项的统计分析结果与无交互作用项的统计分析结果进行对比;示例中交互作用项引起的变异在结果变量的总变异中占到79.20%.在应用结构方程模型分析隐变量产生的效应时,有时候不进行隐变量交互作用的分析可能会产生偏倚.exploring the method of modeling latent variable interaction effect analysis in structural equation modeling and the technique of latent variable interaction effect analysis by SAS software, explicating the basic theory of modeling latent variable interaction effect analysis in structural equation modeling, then demonstrating an artificial example of.latent variable interaction effect analysis, comparing the statistical result of the model including interaction term with that of no interaction term model. The given example showed that the interaction term could lead to 70. 55% variance of the criterion variable. It may give rise to bias not to complement interaction effect analysis in SEM.

关 键 词：隐变量 交互作用 结构方程模型 

分 类 号：O213[理学—概率论与数理统计]