Multivariate Outliers
摘要
In the statistical analysis of data one often is confronted with observations that “appear to be inconsistent with the remainder of that set of data” (Barnett and Lewis, Outliers in Statistical Data3rd edn. Wiley, Chichester, 1994). Although such observations (the outliers) have been subject of numerous investigations, there is no general accepted formal definition of outlyingness. Nevertheless, the outliers describe the abnormal data behaviour, i.e. data which are deviating from the natural data variability (see, for instance, Peña and Prieto, Technometrics 43:286–310, 2001; Filzmoser, A multivariate outlier detection method. In: Proceedings of the Seventh International Conference on Computer Data Analysis and Modeling, Aivazian, S., Filzmoser, P., Kharin, Yu. (Eds.) Belarusian State University, Minsk vol. 1, pp. 18–22, 2004 and Filzmoser et al., Comput. Stat. Data Analy. 52:1694–1711, 2008. for a discussion).