Data Envelopment Analysis (DEA) is a nonparametric approach to evaluating the relative efficiency of decision making units (DMUs) that use multiple inputs to produce multiple outputs. An assumption underlying DEA is that all the data assume the form of specific numerical values. In some applications, however, the data may be imprecise. For instance, some of the data may be known only within specified bounds, while other data may be known only in terms of ordinal relations. DEA with imprecise data or, more compactly, the Imprecise Data Envelopment Analysis (IDEA) method developed in this paper permits mixtures of imprecisely- and exactly-known data, which the IDEA models transform into ordinary linear programming forms. This is carried even further in the present paper to comprehend the now extensively employed Assurance Region (AR) concepts in which bounds are placed on the variables rather than the data. We refer to this approach as AR-IDEA, because it replaces conditions on the variables with transformations of the data and thus also aligns the developments we describe in this paper with what are known as cone-ratio envelopments in DEA. As a result, one unified approach, referred to as the AR-IDEA model, is achieved which includes not only imprecise data capabilities but also assurance region and cone-ratio envelopment concepts.DEA efficiency, imprecise data, assurance regions

No abstract

Data Envelopment Analysis (DEA) models, as ordinarily employed, assume that the data for all inputs and outputs are known exactly. In some applications, however, a number of factors may involve imprecise data, which take forms such as ordinal rankings and knowledge only of bounds. Here we provide an example involving a Korean mobile telecommunication company. The Imprecise Data Envelopment Analysis (IDEA) method we use permits us to deal not only with imprecise data and exact data but also with weight restrictions as in the (now) widely used “Assurance Region” (AR) and “cone-ratio envelopment” approaches to DEA. We also show how to transform AR bounds on the variables, obtained from managerial assessments, for instance, into data adjustments. This involves an extended IDEA model, which we refer to as AR-IDEA. All these uses are illustrated by an example application directed to evaluate efficiencies of branch offices of a telecommunication company in Korea.

No abstract