Font Size:
TRIMMED FACTORIAL K-MEANS
Last modified: 2023-05-17
Abstract
This paper provides the definition of trimmed factorial k-means (TFKM)algorithm. TFKM is a robust version of factorial k-means, where a robust covariancematrix input is used, and outliers in the identified reduced space are iteratively re-moved via a trimming procedure. The selected latent rank, number of clusters andoutlier proportion are those which maximize Hartigan’s statistic.