Test

, Volume 8, Issue 2, pp 255–317

Multivariate L-estimation

  • Ricardo Fraiman
  • Jean Meloche
  • Luis A. García-Escudero
  • Alfonso Gordaliza
  • Xuming He
  • Ricardo Maronna
  • Víctor J. Yohai
  • Simon J. Sheather
  • Joseph W. McKean
  • Christopher G. Small
  • Andrew Wood
  • R. Fraiman
  • Jean Meloche
Article

DOI: 10.1007/BF02595872

Cite this article as:
Fraiman, R., Meloche, J., García-Escudero, L.A. et al. Test (1999) 8: 255. doi:10.1007/BF02595872

Abstract

In one dimension, order statistics and ranks are widely used because they form a basis for distribution free tests and some robust estimation procedures. In more than one dimension, the concept of order statistics and ranks is not clear and several definitions have been proposed in the last years. The proposed definitions are based on different concepts of depth. In this paper, we define a new notion of order statistics and ranks for multivariate data based on density estimation. The resulting ranks are invariant under affinc transformations and asymptotically distribution free. We use the corresponding order statistics to define a class of multivariate estimators of location that can be regarded as multivariate L-estimators. Under mild assumptions on the underlying distribution, we show the asymptotic normality of the estimators. A modification of the proposed estimates results in a high breakdown point procedure that can deal with patches of outliers. The main idea is to order the observations according to their likelihoodf(X1),...,f(Xn). If the densityf happens to be cllipsoidal, the above ranking is similar to the rankings that are derived from the various notions of depth. We propose to define a ranking based on a kernel estimate of the densityf. One advantage of estimating the likelihoods is that the underlying distribution does not need to have a density. In addition, because the approximate likelihoods are only used to rank the observations, they can be derived from a density estimate using a fixed bandwidth. This fixed bandwidth overcomes the curse of dimensionality that typically plagues density estimation in high dimension.

Key Words

Approximate likelihood depthasymptotic normalityequivariancemultivariate order statistics

AMS subject classification

Primary 62G05secondary 62G20

Copyright information

© Sociedad Española de Estadistica e Investigación Operativa 1999

Authors and Affiliations

  • Ricardo Fraiman
    • 2
  • Jean Meloche
    • 1
  • Luis A. García-Escudero
    • 3
  • Alfonso Gordaliza
    • 3
  • Xuming He
    • 4
  • Ricardo Maronna
    • 5
  • Víctor J. Yohai
    • 6
  • Simon J. Sheather
    • 7
  • Joseph W. McKean
    • 8
  • Christopher G. Small
    • 9
  • Andrew Wood
    • 10
  • R. Fraiman
  • Jean Meloche
  1. 1.Department of StatisticsThe University of BritishCanada
  2. 2.Departamento de MatemáticaUniversidad de San AndrésArgentina
  3. 3.University of ValladolidSpain
  4. 4.University of IllinoisUSA
  5. 5.Universidad de La Plata and Comision de Investigaciones Científicas Provincia de Buenos AiresArgentina
  6. 6.Universidad de Buenos Aires and CONICETArgentina
  7. 7.University of New South WalesAustralia
  8. 8.Western Michigan UniversityUSA
  9. 9.University of WaterlooCanada
  10. 10.University of NottinghamUK