Benchmarking South African water utilities using three efficiency analysis methods

Genius Murwirapachena, Johane Dikgang and Richard Mulwa

Applied Economics, 2025, vol. 57, issue 31, 4472-4485

Abstract: This paper compares efficiency scores from the data envelopment analysis (DEA), stochastic frontier analysis (SFA), and stochastic non-parametric envelopment of data (StoNED) methods in the context of regulating South African water utilities. We estimate cost efficiency based on cross-sectional data from 102 South African water utilities in the period 2013/14. We compare the impact of methodological choices on the efficiency scores. For StoNED, we compare scores from two different estimation techniques (method of moments and pseudolikelihood). We also use the naïve method of averaging (NMA) and compare its results to those generated by the other methods. Results show that the choice of method has an impact on efficiency estimates and monetary cost reduction targets. When water sector regulators in the developing countries intend to benchmark utilities based on each of these methods, heterogeneity and the operating environments of utilities should be considered before deciding on the estimation method.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/00036846.2024.2364074 (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:taf:applec:v:57:y:2025:i:31:p:4472-4485

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RAEC20

DOI: 10.1080/00036846.2024.2364074

Access Statistics for this article

Applied Economics is currently edited by Anita Phillips

More articles in Applied Economics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().