Estimation of the European Customer Satisfaction Index: Maximum Likelihood versus Partial Least Squares. Application to Postal Services

摘要

Customer satisfaction and retention are key issues for organizations in today's competitive market place. As such, much research and revenue has been invested in developing accurate ways of assessing consumer satisfaction at both the macro (national) and micro (organizational) level. Since the instigation of the national customer satisfaction indices (CSI), partial least squares (PLS) has been used to estimate the CSI models in preference- to the maximum likelihood approach (ML) to structural equation models because they do not rely on strict assumptions about the data. However, this choice was based upon some misconceptions about the use of ML and does not take into consideration more recent advances, including estimation methods that are robust to non-normality and missing data. In this paper, both ML and PLS approaches were compared by evaluating perceptions of the Isle of Man Post Office Products and Customer service using a CSI format. The new ML procedures were found to be advantageous over PLS as they are both robust and unbiased while PLS are robust but biased. PLS should be used only in soft modelling situations (i.e. small sample sizes, weak theory and large numbers of variables), which are far from the CSI research practice.