Some linear programming methods for frontier estimation

We propose new methods for estimating the frontier of a set of points. The estimates are defined as kernel functions covering all the points and whose associated support is of smallest surface. They are written as linear combinations of kernel functions applied to the points of the sample. The weights of the linear combination are then computed by solving a linear programming problem. In the general case, the solution of the optimization problem is sparse, that is, only a few coefficients are non-zero. The corresponding points play the role of support vectors in the statistical learning theory. In the case of uniform bivariate densities, the L1 error between the estimated and the true frontiers is shown to be almost surely converging to zero, and the rate of convergence is provided. The behaviour of the estimates on one finite sample situation is illustrated on simulations. Copyright © 2005 John Wiley & Sons, Ltd.

[1]  H. Abbar.  Un estimateur spline du contour d'une répartition ponctuelle aléatoire , 1990 .

[2]  Dominique Deprins,et al.  Measuring Labor-Efficiency in Post Offices , 2006 .

[3]  St'ephane Girard,et al.  Central limit theorems for smoothed extreme value estimates of Poisson point processes boundaries , 2003, 1103.5884.

[4]  D. Bosq.  Linear Processes in Function Spaces: Theory And Applications , 2000 .

[5]  J. F. Bonnans.  Optimisation numérique : aspects théoriques et pratiques , 1997 .

[6]  A. Tsybakov,et al.  Estimation of non-sharp support boundaries , 1995 .

[7]  Abraham Charnes,et al.  Measuring the efficiency of decision making units , 1978 .

[8]  S. Girard,et al.  Extreme Values and Haar Series Estimates of Point Process Boundaries , 2003, 1103.5947.

[9]  P. Massart,et al.  Minimum contrast estimators on sieves: exponential bounds and rates of convergence , 1998 .

[10]  Guillaume Bouchard,et al.  Linear programming problems for frontier estimation , 2011, 1103.5925.

[11]  B. Park,et al.  THE FDH ESTIMATOR FOR PRODUCTIVITY EFFICIENCY SCORES , 2000, Econometric Theory.

[12]  Laurent Gardes,et al.  Estimating the support of a Poisson process via the Faber-Schauder basis and extreme values , 2002 .

[13]  Léopold Simar,et al.  Iterated bootstrap with applications to frontier models , 1995 .

[14]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[15]  Pierre Jacob,et al.  Projection estimates of point processes boundaries , 2003, 1103.5938.

[16]  M. Nussbaum,et al.  On the Estimation of a Support Curve of Indeterminate Sharpness , 1997 .

[17]  S. Girard,et al.  Extreme values and kernel estimates of point processes boundaries , 2004, 1103.5931.

[18]  Denis Bosq,et al.  Linear Processes in Function Spaces , 2000 .

[19]  J. Hiriart-Urruty,et al.  Convex analysis and minimization algorithms , 1993 .

[20]  John A. Hartigan,et al.  Clustering Algorithms , 1975 .

[21]  P. Massart,et al.  Risk bounds for model selection via penalization , 1999 .

[22]  Michael Brady,et al.  Novelty detection for the identification of masses in mammograms , 1995 .

[23]  A. Tsybakov,et al.  Efficient Estimation of Monotone Boundaries , 1995 .

[24]  A. Tsybakov,et al.  Minimax theory of image reconstruction , 1993 .

[25]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[26]  P. Jacob,et al.  Estimating the edge of a Poisson process by orthogonal series , 1995 .

[27]  I. Gijbels,et al.  Estimation of a Support Curve via Order Statistics , 2000 .

[28]  L. Devroye,et al.  Detection of Abnormal Behavior Via Nonparametric Estimation of the Support , 1980 .

[29]  B. Park,et al.  A NOTE ON THE CONVERGENCE OF NONPARAMETRIC DEA ESTIMATORS FOR PRODUCTION EFFICIENCY SCORES , 1998, Econometric Theory.

[30]  Peter Hall,et al.  On Pseudodata Methods for Removing Boundary Effects in Kernel Density Estimation , 1996 .

[31]  E. Mammen,et al.  On estimation of monotone and concave frontier functions , 1999 .

[32]  André Hardy,et al.  Une nouvelle approche des problèmes de classification automatique , 1982 .