galts: Genetic algorithms and C-steps based LTS (Least Trimmed Squares) estimation

Share:

This package includes the ga.lts function that estimates LTS (Least Trimmed Squares) parameters using genetic algorithms and C-steps. ga.lts() constructs a genetic algorithm to form a basic subset and iterates C-steps as defined in Rousseeuw and van-Driessen (2006) to calculate the cost value of the LTS criterion. OLS(Ordinary Least Squares) regression is known to be sensitive to outliers. A single outlying observation can change the values of estimated parameters. LTS is a resistant estimator even the number of outliers is up to half of the data. This package is for estimating the LTS parameters with lower bias and variance in a reasonable time. Version 1.3 included the function medmad for fast outlier detection in linear regression.

Author
Mehmet Hakan Satman
Date of publication
2013-02-07 09:27:39
Maintainer
Mehmet Hakan Satman <mhsatman@istanbul.edu.tr>
License
GPL
Version
1.3

View on CRAN

Man pages

ga.lts
Function for estimating the LTS (Least Trimmed Squares)...
galts-package
Genetic algorithms and C-steps based LTS (Least Trimmed...
medmad
Function for detecting regression outliers
medmad.cov
Function for robust covariance matrix estimation.

Files in this package

galts
galts/MD5
galts/man
galts/man/medmad.cov.Rd
galts/man/galts-package.Rd
galts/man/ga.lts.Rd
galts/man/medmad.Rd
galts/NAMESPACE
galts/DESCRIPTION
galts/R
galts/R/medmad.r
galts/R/galts.r