Search Results - subject:"TCLUST"

Robust clustering around regression lines with high density regions

Cerioli, Andrea; Perrotta, Domenico - In: Advances in Data Analysis and Classification 8 (2014) 1, pp. 5-26

Robust methods are needed to fit regression lines when outliers are present. In a clustering framework, outliers can be extreme observations, high leverage points, but also data points which lie among the groups. Outliers are also of paramount importance in the analysis of international trade...

Persistent link: https://www.econbiz.de/10010758714

On the breakdown behavior of the TCLUST clustering procedure

Ruwet, C.; García-Escudero, L.; Gordaliza, A.; … - In: TEST: An Official Journal of the Spanish Society of … 22 (2013) 3, pp. 466-487

solutions. With this in mind, several proposals have been introduced in the literature. The TCLUST procedure works with a … contamination of the TCLUST has already been studied. This paper aims to look at its resistance to a higher amount of contamination … that the TCLUST procedure resists to a proportion α of contamination as soon as the data set is sufficiently “well …

Persistent link: https://www.econbiz.de/10010994276

A fast algorithm for robust constrained clustering

Fritz, Heinrich; García-Escudero, Luis A.; Mayo-Iscar, … - In: Computational Statistics & Data Analysis 61 (2013) C, pp. 124-136

. With this idea in mind, a new algorithm for the TCLUST robust clustering procedure is proposed which implements such …

Persistent link: https://www.econbiz.de/10011056525