Using genetic algorithms as a parameter estimation tool for the generalized lambda distribution (gld) family: “methods of moments”
Palabras clave:
Data Fitting, Generalized Lambda Distribution, Minimization Method, Moments, Percentiles, Genetic AlgorithmsResumen
The generalized lambda distribution, λ,λ,λ,λ(GLD ) 1 432 is a four-parameter family that has been used for fitting distributions to a wide variety of data sets. Minimization through traditional calculus-based methods has been implemented with relative success, but due to computational and theoretical shortcomings of those methods, the moment space has been limited. This paper solve those troubles by using Genetic Algorithms (search algorithms based on the mechanics of natural selection and natural genetics) applied to the methods of moments. Examples of better solutions than the ones find out with traditional calculusbased methods are included.
Descargas
Citas
RAMBERG, J.S., TADIKAMALLA, P.R., DUDEWICZ, E.J., and MIKYTHA, E.F. (1979). “A Probability Distribution And Its Uses In Fitting Data,” Technometrics, 21, 201-214.
GOLDBERG, DAVID. Genetic Algorithms In Search Optimization And Machine Learning. 1990.
NUMERICAL RECIPIES IN C: THE ART OF SCIENTIFIC COMPUTING (ISBN 0-521-43108-5) Copyright (c) 1988-1992 by Cambrige University Press. http://www.nr.com
AYDIN ÖZTÜRK and ROBERT F. DALE (1985), “Least Squares Estimation Of The Parameters Of The Generalized Lambda Distribution”, Technometrics, 27 No. 1, 81 - 84
ZAVEN A. KARIAN and EDWARD J. DUDEWICZ. Fitting Statistical Distributions “The Generalized Lambda Distributions and Generalized Bootstrap Methods”. CRC Press. Boca Raton London New York Washington, D.C. 2000.
FINO RICARDO NELSON, MORENO DAVID LEONARDO. “Método Para Estimar Los Parámetros De La Distribución Lambda Generalizada Basado En Algoritmos Genéticos”. Ingeniería de Sistemas, Universidad Antonio Nariño, Octubre de 2009.
DUDEWICZ, E.J. and KARIAN, Z.A . “Fitting the Generalized Lambda Distribution To Data: a method based on percentiles” ACM Communications in Statistics, 28(3), 793-819 (1999).
Descargas
Publicado
-
Resumen81
-
PDF29
Cómo citar
Número
Sección
Licencia
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.