Show Less
Restricted access

Data Envelopment Analysis: From Normative to Descriptive Performance Evaluation


Nadia Vazquez Novoa

The question of modern performance evaluation has been extensively discussed in the literature, leading to a call for models including non-optimizing behaviors of decision makers and non-financial performance criteria. A promising management instrument is data envelopment analysis (DEA), which enables the aggregation of financial and non-financial indicators into a single measure. This work contributes to a better understanding of DEA from two perspectives: (i) it offers a normative solution to the zero-value weight problem and (ii) it provides the first experimental results on behavioral DEA based on an original taxonomy of cognitive biases related to performance evaluation. Behavioral DEA is a completely new research area which yields plenty of research opportunities.

Show Summary Details
Restricted access

2. DEA from a normative perspective: efficiency and balance scores


← 8 | 9 →

2.   DEA from a normative perspective: efficiency and balance scores17

DEA is a non-parametric methodology for measuring the relative efficiencies of a set of DMUs when several inputs and outputs are available.18 The aim of the present chapter is to introduce the original DEA model as an instrument for relative performance measurement (Subchapter 2.1) and to closely analyze one of its distinctive characteristics: the endogenous weight determination. This property constitutes one of the strengths of DEA, but it may also be associated to the undesired case of zero-value weights. For this reason, value judgment in DEA has been proposed as an alternative for dealing with this issue (Subchapter 2.2). Subchapter 2.3 introduces a new model for measuring the output balance of a set of DMUs which aims to facilitate value judgment in DEA based on the available data, i.e., without requiring managers to define any kind of weight constraints.

2.1   DEA methodology as an instrument for relative performance measurement

2.1.1   Relative performance measurement

You are not authenticated to view the full text of this chapter or article.

This site requires a subscription or purchase to access the full text of books or journals.

Do you have any questions? Contact us.

Or login to access all content.