Abstract Contextual or environmental variables usually play a major role in explaining relative efficiency differences in most empirical applications. Nevertheless, most studies focused on the analysis of productivity changes over a period usually do not account for the influence of these variables, especially those adopting a nonparametric approach. In this paper, we propose a novel method to incorporate information about contextual variables in Malmquist productivity decompositions based on conditional nonparametric efficiency measures. The usefulness of the proposed approach is illustrated on an empirical application using data about European Union (EU) regions to investigate the extent to which the quality of governance influenced the evolution of regional productivity in the years following the last financial crisis. While the index captures productivity change conditional on external factors, such as the quality of governance in our empirical application, it does not allow for formal inference about the marginal effect of these variables. Extending the methodology to address this limitation is beyond the scope of the current paper but represents a promising direction for future research.
Aparicio et al. (Fri,) studied this question.