Abstract
The least trimmed square algorithm is a robust statistical method. Comparing with the classical least square method, it can eliminate the inference of the abnormal observed data in the process of data analysis. But the least trimmed square algorithm has disadvantages, such as on the condition of nonlinear function fitting. On the other hand, the evolution strategy method has the excellent global searching ability. The paper utilizes the evolution strategy algorithm to realize the solution to least square algorithm, which can overcome the disadvantages of the least square algorithm. Some examples show that the method is feasible.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Huber, P.J.: Robust regression: asymptotics, conjectures and Monte Carlo. Ann. Stat. 1, 799–821 (1973)
Rousseeuw, P.J.: Least median of squares regression. Am. Statist. Ass. 79, 871–880 (1984)
Mitchell, M.: An Introduction to Genetic Algorithms. The MIT Press, Cambridge (1996)
Hansen, N., Ostermeier, A.: Completely Derandomized Self-adaptation in Evolution Strategies. Evol. Comput. 45, 159–195 (2001)
Karr, C.L., Weck, B., et al.: Least median squares curve fitting using a genetic algorithm. Engng. Applic. Artif. Intell. 44, 177–189 (1995)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag GmbH Berlin Heidelberg
About this paper
Cite this paper
Dong, Y., Ding, J. (2012). The Evolution Strategy Implementation of the Least Trimmed Square Algorithm. In: Jin, D., Lin, S. (eds) Advances in Computer Science and Information Engineering. Advances in Intelligent and Soft Computing, vol 169. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30223-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-30223-7_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30222-0
Online ISBN: 978-3-642-30223-7
eBook Packages: EngineeringEngineering (R0)