Advances in Data Analysis and Classification

, Volume 4, Issue 4, pp 301–334

Outlier detection and robust covariance estimation using mathematical programming

Regular Article

DOI: 10.1007/s11634-010-0070-7

Cite this article as:
Nguyen, TD. & Welsch, R.E. Adv Data Anal Classif (2010) 4: 301. doi:10.1007/s11634-010-0070-7

Abstract

The outlier detection problem and the robust covariance estimation problem are often interchangeable. Without outliers, the classical method of maximum likelihood estimation (MLE) can be used to estimate parameters of a known distribution from observational data. When outliers are present, they dominate the log likelihood function causing the MLE estimators to be pulled toward them. Many robust statistical methods have been developed to detect outliers and to produce estimators that are robust against deviation from model assumptions. However, the existing methods suffer either from computational complexity when problem size increases or from giving up desirable properties, such as affine equivariance. An alternative approach is to design a special mathematical programming model to find the optimal weights for all the observations, such that at the optimal solution, outliers are given smaller weights and can be detected. This method produces a covariance estimator that has the following properties: First, it is affine equivariant. Second, it is computationally efficient even for large problem sizes. Third, it easy to incorporate prior beliefs into the estimator by using semi-definite programming. The accuracy of this method is tested for different contamination models, including recently proposed ones. The method is not only faster than the Fast-MCD method for high dimensional data but also has reasonable accuracy for the tested cases.

Keywords

Covariance matrix estimation Robust statistics Outlier detection Optimization Semi-definite programming Newton–Raphson method 

Mathematics Subject Classification (2000)

62-07 (Statistics-Data analysis) 90-08 (Operations Research-Computational methods) 

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.3103 Newmark Civil Engineering Laboratory, UIUCUrbanaUSA
  2. 2.Center for Computational Research in Economics and Management ScienceSloan School of Management, MITCambridgeUSA

Personalised recommendations