Loading...
Value of the stochastic efficiency in data envelopment analysis
Vincent, Charles
Vincent, Charles
Publication Date
15/09/2017
End of Embargo
Supervisor
Rights
© 2017 Elsevier Ltd. All rights reserved. Reproduced in accordance with the publisher's self-archiving policy. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.
Peer-Reviewed
Yes
Open Access status
openAccess
Accepted for publication
27/03/2017
Institution
Department
Awarded
Embargo end date
Collections
Additional title
Abstract
This article examines the potential benefits of solving a stochastic DEA model over solving a deterministic DEA model. It demonstrates that wrong decisions could be made whenever a possible stochastic DEA problem is solved when the stochastic information is either unobserved or limited to a measure of central tendency. We propose two linear models: a semi-stochastic model where the inputs of the DMU of interest are treated as random while the inputs of the other DMUs are frozen at their expected values, and a stochastic model where the inputs of all of the DMUs are treated as random. These two models can be used with any empirical distribution in a Monte Carlo sampling approach. We also define the value of the stochastic efficiency (or semi-stochastic efficiency) and the expected value of the efficiency.
Version
Accepted manuscript
Citation
Vincent C and Cornillier F (2017) Value of the stochastic efficiency in data envelopment analysis. Expert Systems with Applications. 81: 349-357.
Link to publisher’s version
Link to published version
Link to Version of Record
Type
Article