A Well-defined Efficiency Measure for Dealing with Interval-Scale Data: Some Properties

One of the main assumptions in Data Envelopment Analysis (DEA) is that all the data are measured in a ratio-scale. However, in some applications we may deal with interval-scale data. In these cases, traditional DEA models are not generally reliable. Here, we formulate a modification of the additive model which is not only translation invariant, but also provides an efficiency score for each unit. Furthermore, we investigate the main properties of the obtained efficiency measure which show that this score is well-defined based on some pre-defined criteria.