Multivariate outliers may be modeled using the contaminated multivariate normal distribution with two parameters indicating the percentage of outliers and the degree of contamination. Recent developments in elliptical distribution theory are used to determine estimators of these parameters. These estimators can be used with an index of Mahalanobis distance to identify the multivariate outliers, which can then be eliminated to obtain approximately normal data. The performance of the proposed estimators and outliers rejection procedures are evaluated in a small simulation study.
Get full access to this article
View all access options for this article.
References
1.
BERKANE, M.
and P. M. BENTLER (1986) “Moments of elliptically distributed random variates.”Statistics & Probability Letters4: 333-335.
2.
BERKANE, M.
and P. M. BENTLER (1987) “Characterizing parameters of multivariate elliptical distributions.”Communication Stat. Simulation16: 193-198.
3.
DEVLIN, S. J.
, R. GNANADESIKAN, and J. R. KETTENRING (1981) “Robust estimation of dispersion matrices and principal components.”J. Amer. Stat. Assn.76: 354-362.
4.
HUBER, P. J.
(1977) Robust Statistical Procedures. Philadelphia: Society for Industrial and Applied Mathematics.
5.
LITTLE, R.J.A.
and D. B. RUBIN (1987) Statistical Analysis with Missing Data. New York: John Wiley.
6.
MARDIA, K. V.
(1970) “Measures of multivariate skewness and kurtosis with applications.”Biometrika57: 519-530.
