A use of a nonparametric statistic for DEA frontier shift: the Kruskal and Wallis rank test

摘要

A new use of the nonparametric statistic, referred to as the "Kruskal and Wallis rank test", is proposed in this study. The nonprametric statistic examines whether or not any frontier shift occurs among observed periods. To document its practicality, the proposed statistic is incorporated into the framework of Window Malmquist Analysis (WMA) that is structured by combining Data Envelopment Analysis (DEA) window analysis with the Malmquist index approach. As an important case study, this research applies the new technique to examine the performance of Japanese postal services from 1983 to 1997. Two policy implications are derived from the empirical study.