Developing a Discriminant Index to Determine Critical Service Attributes of Continuous Performance Improvement

Abstract

A performance evaluation matrix (PEM) presents the overall performance of an organization and provide reference for improvement strategies. PEMs are widely applied in the assessment of service performance in various organizations. Customer ratings of importance and satisfaction are used to calculate point estimates which are then plotted in PEMs. Their locations in the PEM show whether performance is good. Researchers have replaced these point estimates with the joint confidence interval of two indices to reduce the uncertainties caused by sampling errors and prevent misjudgment. However, this approach is quite complicated for practice application. For this reason, we defined a discriminant index based on PEM concepts. Our index uses the difference between the importance and satisfaction indices to solve the aforementioned issues in performance evaluation and help managers determine performance quality more easily. The joint confidence interval of the two indices serves as the feasible region, and we used linear programming to solve the upper confidence limit of the discriminant index, then performed statistical hypothesis testing using this upper confidence limit to determine whether a service item falls within the “needs improvement” zone. Finally, we present a case study to demonstrate the applicability of the proposed model by assessing a computer-assisted language learning (CALL) system.