Detecting Outliers in Frontier Models: A Simple Approach

By Léopold Simar. 2003

381 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/929804ec35457b2a611650a8d0bc74f4ada7b1da

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Management Science and Operations Research

Citations in the corpus

Technical Efficiency of the Brazilian Municipalities: Correcting Nonparametric Frontier Measurements for Outliers (2005, background): “More recent developments of this important issue include the order-m frontiers (Cazals et al., 2002; Simar, 2003 ) and the Robust Efficiency Frontier (Kuosmanen and Post, 1999; Cherchye et al., 2000).”
Robustness and inference in nonparametric partial frontier modeling (2011, methodology): “A basic tool can be found in Simar (2003) and Daraio and Simar (2007) consisting of a picture showing the evolution of the “proportion” of sample points outside either the order-m or order-α frontier as a function of the order and of another tuning parameter.”
How to improve the performances of DEA/FDH estimators in the presence of noise? (2007, positive): “As pointed in Simar (2003) , it is not a surprise that different techniques for detecting outliers provide different warnings, but looking to the stochastic FDH results, the analysis would rather conclude here (with caution due to the small sample size) in the presence of noise in this data set, ra”
Conditional nonparametric frontier models for convex and nonconvex technologies: a unifying approach (2007, methodology): “These percentages have been used in Simar (2003) to warn or detect potential outliers in the data set.”
How to measure the impact of environmental factors in a nonparametric production model (2012, background): “But for finite n (as we use in practice), (n) will be less than 1 (and m(n) will be less than infinity) and so the corresponding estimate 11 of the full frontier will not envelop all the data points being more robust and resistant to outliers and extreme values than the standard envelopment estimato”
The contributions of human capital, R&D spending and convergence to total factor productivity growth (2018, methodology): “The sample size for regressions based on the Malmquist index is smaller, since the outlier detection by Simar (2003) is applied.”
The Cost Efficiency of German Banks: A Comparison of Sfa and DEA (2006, background): “Detecting outliers is not an easy task for multivariate analysis (Simar, 2003).”
Probabilistic characterization of directional distances and their robust versions (2012, background): “This idea has been suggested in Simar (2003), proposing to do this kind of analysis in a more systematic way.”
Non-parametric, unconditional quantile estimation for efficiency analysis with an application to Federal Reserve check processing operations (2005, neutral): “Although several methods have been proposed for detecting outliers in highdimensional data (e.g., Wilson, 1993, 1995; Kuntz and Scholtes, 2000; Simar, 2003; and 9 The faster convergence rate of DEA estimators results from convexification of the free-disposal hull of the data, but DEA estimators are…”
Estimation and Inference in Nonparametric Frontier Models: Recent Developments and Perspectives (2013, background): “A number of techniques exist for finding outliers in frontier settings (e.g., Wilson, 1993, 1995; Simar, 2003; Porembski et al., 2005), Alternatively, one can use robust, partial frontier estimators, which also offer other advantages.”
Robust nonparametric estimators of monotone boundaries (2005, methodology): “The advantage of the orderm frontiers lies in the fact that they can be easily extended to the full multivariate case ( X ∈ Rp+ andY ∈ Rq+), where they can be computed by using a Monte-Carlo algorithm ( [15]).”
Creating composite indicators with DEA and robustness analysis: the case of the Technology Achievement Index (2008, positive): “Such issues have been addressed rather infrequently in the DEA literature (Valdmanis, 1992; Wilson, 1995; Banker et al, 1996; Simar and Wilson, 1998; Simar, 2003).”
Introducing Environmental Variables in Nonparametric Frontier Models: a Probabilistic Approach (2005, methodology): “The quality of the approximation can be tuned by increasing B but in most applications, say B = 200, seems to be a reasonable choice (see Simar, 2003, for a code written in Matlab).”
FEAR: A software package for frontier efficiency analysis with R (2008, methodology): “sw98 implements the bootstrap algorithm described by Simar and Wilson (1998); this command can be used to estimate 95-percent confidence intervals for the input distance functions corresponding to each observation in the Charnes et al.”