A comparison of algorithms for the multivariate L1-median

被引：0
作者：
Heinrich Fritz
Peter Filzmoser
Christophe Croux
机构：
[1] Vienna University of Technology,Department of Statistics and Probability Theory
[2] K. U. Leuven University,Faculty of Business and Economics
[3] Tilburg University,Faculty of Business and Economics
来源：
Computational Statistics | 2012年 / 27卷
关键词：
Algorithm; Multivariate median; Optimization; Robustness;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The L1-median is a robust estimator of multivariate location with good statistical properties. Several algorithms for computing the L1-median are available. Problem specific algorithms can be used, but also general optimization routines. The aim is to compare different algorithms with respect to their precision and runtime. This is possible because all considered algorithms have been implemented in a standardized manner in the open source environment R. In most situations, the algorithm based on the optimization routine NLM (non-linear minimization) clearly outperforms other approaches. Its low computation time makes applications for large and high-dimensional data feasible.
引用
收藏
页码：393 / 410
页数：17
相关论文
共 31 条
[1]  
Bedall F(1979)As 143: the mediancentre Appl Stat 28 325-328
[2]  
Zimmermann H(1996)On a geometric notion of quantiles for multivariate data J Am Statist Assoc 91 862-872
[3]  
Chaudhuri P(2005)High breakdown estimators for principal components: the projection- pursuit approach revisited J Multivar Anal 95 206-226
[4]  
Croux C(2007)Algorithms for projection-pursuit robust principal component analysis Chemometr Intell Lab Syst 87 218-225
[5]  
Ruiz-Gazen A(2010)Detecting influential observations in Kernel PCA Comput Stat Data Anal 54 3007-3019
[6]  
Croux C(1964)Function minimization by conjugate gradients Comput J 7 148-154
[7]  
Filzmoser P(2008)Robust functional estimation using the median and spherical principal components Biometrika 95 587-600
[8]  
Oliveira M(1974)As 78: the mediancentre J R Statist Soc 23 466-470
[9]  
Debruyne M(1995)Generalizing univariate signed rank statistics for testing and estimating a multivariate location parameter Nonparametr Statist 4 293-308
[10]  
Hubert M(1991)Breakdown points of affine equivariant estimators of multivariate location and covariance matrices Ann Stat 19 229-248
1234