Image of the performance boundary for inefficient units in data envelopment analysis with integer values

The aim of this study is investigation effect of integer data in data envelopment analysis (DEA). Theinputs and outputs in different types of DEA are considered to be continuous. In most applicationorientedproblems, some or all of them are integers; and subsequently, the continuous condition of thevalues is omitted. For example, situations in which the inputs/outputs are representatives of the numberof cars, people, etc. In fact, the benchmark unit is artificial and does not contain integer inputs/outputsafter projection on the efficiency frontier. By rounding off the projection point includes integer valueswhich mostly is not in the feasible region or gives another inefficient DMU. In such cases, it is requiredto provide a benchmark unit such that the considered unit reaches the efficiency. In the present shortcommunication, by proposing a novel algorithm, the projecting of an inefficient DMU is carried out insuch a way that produced benchmarking takes values with fully integer inputs/outputs.

Keywords:

data Envelopment Analysis (DEA) , inefficient units , benchmarking