Technical Efficiency of the Brazilian Municipalities: Correcting Nonparametric Frontier Measurements for Outliers

Abstract

In this paper we estimate the DEA technical efficiency for 4796 Brazilian municipalities, by applying a recently proposed “Jackstrap” method, which combines Bootstrap and Jackknife resampling techniques, to reduce the effect of outliers and possible errors in the data set. We perform calculations to identify and eliminate high leverage municipalities, using different variants of Data Envelopment Analysis (DEA), as well as Free Disposal Hull (FDH). Corroborating previous results, efficiency results for the Brazilian municipalities show a clear relationship between the size of the municipality and its efficiency scores. Indeed, under both DEA variants, smaller cities tend to be less efficient than larger ones hence indicating that the quality of the frontier adjustment improves significantly as the size of the municipality increases. We present arguments that may explain to some extent these findings, such as economies of scale and the excess spending due to revenue from royalties. However, such effects require further, more careful examination. Copyright Springer Science+Business Media, Inc. 2005data envelopment analysis, outlier detection, leverage,

Influential observations in frontier models, a robust non-oriented approach to the water sector

“…As a first outlier detection procedure, we select the 'leverage' concept which explicitly exploits the disproportional influence of atypical observations (Sousa and Stosic 2005). For each observation, the leverage (l o ) is measured as the standard deviation of the inefficiency estimates relative to the full sample without the evaluated observation (β m,io ), and the inefficiency estimates relative to the full sample (β m,i ).…”

COOPER-framework: A unified process for non-parametric projects

“…The literature developed several techniques to detect influential observations: the peer count index (Charnes et al, 1985), outlier detection by the use of super-efficiency model (Andersen and Petersen, 1993), order-m based models (Simar, 2003), leverage (Sousa and Stosic, 2005), etc.…”

“…Missing data Kao andLiu, 2000 andKuosmanen, 2009 Negative data Emrouznejad et al, 2009 andPortela et al, 2004 Zero data Thompson et al, 1993 Ratio data Emrouznejad and Amin, 2009 Noisy data Zhu and Cook;Wilson, 2007 Atypical observations Charnes et al, 1985;Andersen and Petersen, 1993;Simar, 2003;Sousa and Stosic, 2005;Langford and Lewis, 1998 Operational models Parametric models -To investigate possibility of using parametric vs non-parametric models, within these whether to use deterministic or stochastic models.…”

Financial Efficiency Analysis of Metropolitan Municipalities With Integrated Dea and Gra: The Case of Turkey

“…When studies related to the efficiency of municipalitiesare examined, evidence indicates that DEA is more frequently used in identifying efficiency (Kloot, 1999;Poister and Streib, 1999;Prieto and Zofio, 2001;Çağlar, 2003;Woodbury and Dollery, 2004;Sousa and Stosic, 2005;Doğan, 2006;Loikkanen andSusiluoto, Yıl:8 Sayı:15, Yaz 2015 ISSN 1307-9832 2006; Balaguer-Coll et al, 2007;Afonso and Fernandes, 2008;Nijkamp and Suzuki, 2009;Boetti et al, 2009, Kalb, 2010aKalb et al, 2012, Giordano andTommasino, 2011;Storto, 2013). However, no studies have been undertaken in which efficient units are sequenced according to their performances and these efficiencies are examined within themselves.…”