Statistical Papers

, Volume 55, Issue 1, pp 49–69

Fast nonparametric classification based on data depth

Authors

  • Tatjana Lange
    • Hochschule Merseburg, Geusaer Straße
    • Universität zu Köln, Albertus-Magnus-Platz
  • Pavlo Mozharovskyi
    • Universität zu Köln, Albertus-Magnus-Platz
Regular Article

DOI: 10.1007/s00362-012-0488-4

Cite this article as:
Lange, T., Mosler, K. & Mozharovskyi, P. Stat Papers (2014) 55: 49. doi:10.1007/s00362-012-0488-4

Abstract

A new procedure, called DDα-procedure, is developed to solve the problem of classifying d-dimensional objects into q ≥ 2 classes. The procedure is nonparametric; it uses q-dimensional depth plots and a very efficient algorithm for discrimination analysis in the depth space [0,1]q. Specifically, the depth is the zonoid depth, and the algorithm is the α-procedure. In case of more than two classes several binary classifications are performed and a majority rule is applied. Special treatments are discussed for ‘outsiders’, that is, data having zero depth vector. The D Dα-classifier is applied to simulated as well as real data, and the results are compared with those of similar procedures that have been recently proposed. In most cases the new procedure has comparable error rates, but is much faster than other classification approaches, including the support vector machine.

Keywords

Alpha-procedureZonoid depthDD-plotPattern recognitionSupervised learningMisclassification rateSupport vector machine

Copyright information

© Springer-Verlag Berlin Heidelberg 2012