SciELO - Scientific Electronic Library Online

 
vol.28 issue2Multicolinearity Detection by Means of the h-Plot of the Correlation Matrix InverseApplication of Generalized Linear Models to Data Analysis in Drinking Water Treatment author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Revista Colombiana de Estadística

Print version ISSN 0120-1751

Rev.Colomb.Estad. vol.28 no.2 Bogotá July/Dec. 2005

 

Métodos numéricos para la estimación de parámetros en regresión cuantílica

Numerical Methods to Estimate Parameters in Quantile Regression

HÉCTOR MANUEL MORA ESCOBAR1

1Departamento de Matemáticas, Universidad Nacional de Colombia, Bogotá, E-mail: hmmorae@unal.edu.co


Resumen

La regresión cuantílica es un problema de optimización convexa no diferenciable. Se examinan las ventajas y desventajas con relación a la necesidad de recursos de memoria y tiempo de cálculo de tres métodos clásicos de solución: dos de optimización lineal y el método de planos de corte.

Palabras Clave: regresión cuantílica, optimización lineal, optimización no diferenciable, planos de corte.


Abstract

Quantile regression is a nondifferentiable convex optimization problem. We compare three classical numerical methods, two of them based on linear optimization, and the cutting plane method. We compare them by their re quired memory and computing time.

Keywords: quantile regression, linear programming, nondifferentiable optimization, cutting planes.


Texto completo disponible en PDF


Referencias

1. Cade, B. & Noon, B. (2003), "A Gentle Introduction to Quantile Regression for Ecologists", Frontiers in Ecology and the Environment 1(8), 412-420.        [ Links ]

2. Cheney, E. & Goldstein, A. (1959), "Newton"s Method for Convex Programming ans Tchebycheff Approximations", Numerische Mathematik (1), 253-268.        [ Links ]

3. Du Merle, O. (1995), Points intérieurs et plans coupants : mise en oeuvre et développement d"une méthode pour l"optimisation convexe et la programmation linéaire structurée de grand taille, PhD thesis, Universidad de Ginebra.        [ Links ]

4. Fitzenberger, B., Koenker, R. & Machado, J. (2002), Economic Applications of Quantile Regression, Physica-Verlag, Heidelberg.        [ Links ]

5. Goffin, J., Haurie, A. & Vial, J. (1992), "Decomposition and Nondifferentiable Optimization with the Projective Algorithm", Management Science 38(2), 284-302.        [ Links ]

6. Kelley, J. (1960), "The Cutting Plane Method for Convex Problems", J. SIAM (8), 703-712.        [ Links ]

7. Koenker, R. & Basset, G. J. (1978), "Regression Quantiles", Econometrica 46(1), 33-50.        [ Links ]

8. Sagastizábal, C. (1997), Optimisation non Differérentiable en Bonnans J.F. et al., Optimisation Numérique, Springer, Paris.        [ Links ]

9. Silva, M.A. Arenales, M. (2000), "Uma extensão do método simplex para a resolucão do problema de regressão quantil", Rev. Mat. Est., São Paulo (18), 125-144.        [ Links ]

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License