Handling estimated proportions in public sector data envelopment analysis

Mehmet Ceyhan and James Benneyan ()
Additional contact information
James Benneyan: http://www.coe.neu.edu/healthcare

Annals of Operations Research, 2014, vol. 221, issue 1, 107-132

Abstract: Periodically data envelopment analysis (DEA) is conducted on values that include estimated proportions, such as defect, satisfaction, mortality, or adverse event rates computed from samples. This occurs frequently in healthcare and public sector analysis where proportions frequently are estimated from partial samples. These estimates can produce statistically biased and variable estimates of DEA results, even as sample sizes become fairly large. This paper discusses several approaches to these problems, including Monte Carlo (MC), bootstrapping, chance constrained, and optimistic/pessimistic DEA methods. The performance of each method was compared using previously published data for fourteen Florida juvenile delinquency programs whose two of three inputs and one output were proportions. The impact of sample size and number of estimated rates also were investigated. In most cases, no statistically significant differences were found between the true DEA scores and the midpoints of optimistic/pessimistic, MC, and bootstrap intervals, the latter two after bias correction. True DEA results are strongly correlated with those produced by the MC (r=0.9865, p>0.001), chance constraint (r=0.9536,p>0.001), bootstrapping (r=0.9368,p>0.001), and optimistic/pessimistic (r=0.6799,p>0.001) approaches. While all methods perform fairly well, the MC approach tends to produce slightly better results and be fairly easy to implement. Copyright Springer Science+Business Media, LLC 2014

Keywords: Data envelopment analysis; Stochastic DEA; Bootstrapping; Chance constraint DEA; Bayesian inference (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://hdl.handle.net/10.1007/s10479-011-1007-z (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:annopr:v:221:y:2014:i:1:p:107-132:10.1007/s10479-011-1007-z

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-011-1007-z

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().