On return to scale of fully efficient DMUs in data envelopment analysis under interval data

Recently Cooper et al. [Manage. Sci. 45 (1999) 597] proposed imprecise data envelopment analysis (IDEA). A situation in which some or all data are unknown. The data in IDEA could be interval data, ordinal data or data with bounded ratio. Usually in such cases the corresponding data envelopment analysis models becomes non-linear. When data assume to be interval, decision making units (DMUs) can divide to three classes as follows: (i) efficient in any cases (ii) efficient in maximal sense (iii) always inefficient. In this paper we investigate to the return to scale of DMUs that are locate in first class. Also we introduce models that use exact data and present a combination (if any) which via that the DMU becomes a most productive scale size. (C) 2003 Elsevier Inc. All rights reserved.