Explaining DEA Technical Efficiency Scores in an Outlier Corrected Environment: The Case of Public Services in Brazilian Municipalities

Maria da Conceição Sampaio de Sousa, Francisco Cribari-Neto and Borko D. Stosic

Brazilian Review of Econometrics, 2005, vol. 25, issue 2

Abstract: We estimate DEA (Data Envelopment Analysis) technical efficiency scores for nearly five thousand Brazilian municipalities using a recently proposed method that combines bootstrap and jackknife resampling to eliminate the influence of outliers and possible measurement and recording errors in the data. We use both the constant and variable returns to scale variants of the DEA method. After computing the efficiency scores, we use econometric methods to investigate the determinants of those scores. The results reveal that: (a) the level of computer usage (a proxy for administrative capability) tends to have a positive and highly significant impact on efficiency; such gains seem to be greater for the most inefficient municipalities, thus indicating the existence of diminishing marginal benefits; (b) the urbanization rate is also shown to be positively correlated with the efficiency measures; (c) excess spending due to royalty revenues and economies of scale seem to explain why efficiency scores increase with the size of the municipality; (d) municipalities which take part in the Alvorada Program (a federal program for low income communities) tend to display higher efficiency scores than those they would have achieved had they not been included in the project. Additionally, the results show that the more power awarded to municipal councils, the better the effectiveness in resource utilization as measured by efficiency indices. This is because such councils tend to increase the transparency of the budgeting process, hence reducing corruption and the misuse of local funds.

Date: 2005
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (18)

Downloads: (external link)
https://periodicos.fgv.br/bre/article/view/2507 (text/html)

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:sbe:breart:v:25:y:2005:i:2:a:2507

Access Statistics for this article

Brazilian Review of Econometrics is currently edited by Daniel Monte

More articles in Brazilian Review of Econometrics from Sociedade Brasileira de Econometria - SBE Contact information at EDIRC.
Bibliographic data for series maintained by Núcleo de Computação da FGV EPGE ().