Maximum trimmed likelihood estimator for multivariate mixed continuous and categorical data

Abstract

Abstract In this article we apply the maximum trimmed likelihood (MTL) approach (Hadi and Luceño 1997) to obtain the robust estimators of multivariate location and shape, especially for data mixed with continuous and categorical variables. The forward search algorithm (Atkinson 1994) is adapted to compute the proposed MTL estimates. A simulation study shows that the proposed estimator outperforms the classical maximum likelihood estimator when outliers exist in data. Real datasets are also used to illustrate the method and results of the detection of the outliers.

DOI: 10.1016/j.csda.2007.06.026

12 Figures and Tables

Cite this paper

@article{Cheng2008MaximumTL, title={Maximum trimmed likelihood estimator for multivariate mixed continuous and categorical data}, author={Tsung-Chi Cheng and Atanu Biswas}, journal={Computational Statistics & Data Analysis}, year={2008}, volume={52}, pages={2042-2065} }