摘要：In this paper, regional efficiency of Croatian counties is measured in three-year period (2005-2007) using Data Envelopment Analysis (DEA). The set of inputs and outputs consists of seven socioeconomic indicators. Analysis is carried out using models with assumption of variable returns-to-scale. DEA identifies efficient counties as benchmark members and inefficient counties that are analyzed in detail to determine the sources and the amounts of their inefficiency in each source. To enable proper monitoring of development dynamics, window analysis is applied. Based on the results, guidelines for implementing necessary improvements to achieve efficiency are given. Analysis reveals great disparities among counties. In order to alleviate naturally, historically and politically conditioned unequal county positions over which economic policy makers do not have total control, categorical approach is introduced as an extension to the basic DEA models. This approach, combined with window analysis, changes relations among efficiency scores in favor of continental counties.
