基于PLS-结构方程的顾客满意度评价方法

Method on customer satisfaction assessment based on the partial least square for structural equation

传统结构方程模型虽然在分析中既能处理测量误差,又可描述潜变量之间的结构关系.但是,在求解结构方程模型的过程中严格依赖协方差矩阵,并且假设测量变量服从正态分布,由于顾客满意的频数分布常常为非正态分布,从而极大限制了该方法在顾客满意度研究方面的应用.本文研究基于PLS的结构方程模型,有效解决了在构造客户满意度模型中所遇到的变量非正态问题.并以PLS—结构方程原理为支撑,对商品房顾客满意度问题进行了应用研究.

Although Structural equation models with latent variables represent a considerable step forward to study measurement error and variable＇ s relationship, the arithmetic of model depends on the covariance matrix, and the hypothesis of observable variables distribution is normal. As the frequency distribution of customer satisfaction is non-normal, its application in customer satisfaction is restricted. The arithmetic of partial least square for structural equation modeling is presented to solve the problem in this paper. The customer satisfaction of real estate industry is studied.