Abstract: In this paper, we investigate the problem of nonparametric monotone frontier estimation from the perspective of extreme value theory. This enables us to revisit the asymptotic theory of the popular free disposal hull estimator in a more general setting, to derive new and asymptotically Gaussian estimators and to provide useful asymptotic confidence bands for the monotone boundary function. The finite-sample behavior of the suggested estimators is explored via Monte Carlo experiments. We also apply our approach to a real data set based on the production activity of the French postal services.
Recommendations
- Extreme value statistics and traveling fronts: Various applications
- Bivariate extreme value theory: Models and estimation
- scientific article; zbMATH DE number 1194772
- Tail estimates motivated by extreme value theory
- Estimation and uncertainty quantification for extreme quantile regions
- Semiparametric estimation of extremes
- Extreme value theory and VaR computation
- scientific article; zbMATH DE number 4100396
Cites work
- scientific article; zbMATH DE number 4030574 (Why is no real title available?)
- A moment estimator for the index of an extreme-value distribution
- Advanced robust and nonparametric methods in efficiency analysis. Methodology and applications
- Asymptotic Statistics
- Efficient estimation of monotone boundaries
- Estimation of a support curve via order statistics
- Estimation of non-sharp support boundaries
- Heavy-Tail Phenomena
- Limit theorems for boundary function estimators.
- NONPARAMETRIC FRONTIER ESTIMATION: A CONDITIONAL QUANTILE-BASED APPROACH
- Nonparametric frontier estimation: A robust approach.
- On polynomial estimators of frontiers and boundaries
- On the estimation of a support curve of indeterminate sharpness
- On the estimation of the extreme-value index and large quantile estimation
- Robust nonparametric frontier estimators: qualitative robustness and influence function
- Statistical inference using extreme order statistics
- The FDH estimator for productivity efficiency scores
Cited in
(28)- Frontier estimation with kernel regression on high order moments
- Regularization of nonparametric frontier estimators
- ROBUSTIFIED EXPECTED MAXIMUM PRODUCTION FRONTIERS
- Extreme M-quantiles as risk measures: from \(L^{1}\) to \(L^{p}\) optimization
- Asymptotic properties of nonparametric frontier estimators
- The stochastic approximation method for recursive kernel estimation of the conditional extreme value index
- Probabilistic characterization of directional distances and their robust versions
- Large deviation properties for empirical quantile-type production functions
- A moment estimator for the conditional extreme-value index
- Robust estimation in stochastic frontier models
- On Estimation of Monotone and Concave Frontier Functions
- Quasi-Bayesian Inference for Production Frontiers
- Frontier estimation with local polynomials and high power-transformed data
- Measuring firm performance using nonparametric quantile-type distances
- On kernel smoothing for extremal quantile regression
- Robustness and inference in nonparametric partial frontier modeling
- GMM quantile regression
- A \(\Gamma\)-moment approach to monotonic boundary estimation
- Identification of mixture models using support variations
- Fast and efficient computation of directional distance estimators
- Statistical Approaches for Non‐parametric Frontier Models: A Guided Tour
- On projection-type estimators of multivariate isotonic functions
- Estimation of extreme quantiles from heavy-tailed distributions in a location-dispersion regression model
- Frontier estimation in nonparametric location-scale models
- Kernel estimation of extreme regression risk measures
- Extreme value statistics and traveling fronts: Various applications
- Frontier estimation in the presence of measurement error with unknown variance
- Nonparametric instrumental variables estimation for efficiency frontier
This page was built for publication: Frontier estimation and extreme value theory
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q627286)
