The input and output values that would render an inefficient unit relatively efficient. Thanassoulis and Dyson (1992) examine ways of modifying the DEA model so as to set priorities over which targets should be improved. [Thanassoulis E and Dyson R G (1992) ‘Estimating preferred target input-output levels using data envelopment analysis’, J. of Opi. Res., 56, pp 80-97.]

Same as aggregate efficiency

An efficiency measure that ignores the impact of scale-size by comparing a DMU only to other units of similar scale. Technical efficiency is computed using the BCC model. Overall efficiency is sometimes referred to as technical efficiency as closely follows the concept of technical efficiency developed by Farrell (1957), which technical efficiency as defined here, is known as ‘pure technical efficiency’. [Farrell M J (1957), ‘The measurement of productive efficiency’, J. Roy. Statist. Soc., 120, pp 253-290.]

Simply stated, a unit is Pareto-efficient when an attempt to improve on any of its inputs or outputs will adversely affect some other inputs or outputs. Formally, Chames et al (1981) consider a DMU to be 100% efficient only when ‘none of its inputs can be decreased without either (i) decreasing some of its outputs, or (ii) increasing some of its other inputs, and none of its outputs can be increased without either (i) increasing one or more of its inputs or (ii) decreasing some of its other outputs’. Since the condition for Pareto-efficiency is that a DMU’s efficiency score is 1, efficiency and Pareto-efficiency are synonymous. [Chames A, Cooper W W and Rhodes E (1981), ‘Evaluating program and managerial efficiency: an application of data envelopment analysis to program follow through’, Mgmt. Sci., 6, pp 668-697.]

The operational practices (a combination of the management and engineering knowledge) that determine how a DMU’s inputs are transformed into outputs.

Another name for reference set

Short for decision making unit or DMU.

An efficiency frontier is piecewise linear when the underlying production function is approximated through interconnected linear segments. The basic DEA models are all piecewise linear. See Chames et al (1981) for implications. [Chames A, Cooper W W and Rhodes E (1981), ‘Evaluating program and managerial efficiency: an application of data envelopment analysis to program follow through’, Mgmt. Sci., 6, pp 668-697.]

Yet another name for the efficiency frontier, this term emphasises the fact that each segment of the frontier represents the trade-off possibilities that can be made between the inputs or outputs of a given DMU on the isoquant segment while keeping the DMU efficient.

The primal model allows the DMU being measured to determine the set of optimal weights for each of its factors (outputs are denoted by y. and inputs by x in the following model) so as to maximise its efficiency. The solution consists of a set of weights (for outputs and y for inputs) chosen so that the efficiency of any other unit with these weights won’t exceed 1, the value at which a unit is relatively efficient. Which model is denoted primal and which dual is arbitrary, some authors prefer to call this model the primal model, as it conveys better the basic idea behind DEA. The convention followed here is the same as that used by the developers in their original paper, Chames et al (1978).