An iteratively reweighted approach for robust clustering is presented in this work. The method is initialized with a very robust clustering partition based on an high trimming level. The initial partition is then refined to reduce the number of wrongly discarded observations and substantially increase efficiency. Simulation studies and real data examples indicate that the final clustering solution has both good properties in terms of robustness and efficiency, and naturally adapts to the true underlying contamination level.
Dotto, F., Farcomeni, A., García Escudero, L.a., Mayo Iscar, A. (2018). A reweighting approach to robust clustering. STATISTICS AND COMPUTING, 28(2), 477-493 [10.1007/s11222-017-9742-x].
A reweighting approach to robust clustering
FARCOMENI, Alessio;
2018-01-01
Abstract
An iteratively reweighted approach for robust clustering is presented in this work. The method is initialized with a very robust clustering partition based on an high trimming level. The initial partition is then refined to reduce the number of wrongly discarded observations and substantially increase efficiency. Simulation studies and real data examples indicate that the final clustering solution has both good properties in terms of robustness and efficiency, and naturally adapts to the true underlying contamination level.File | Dimensione | Formato | |
---|---|---|---|
Dotto_Reweighting-Approach_2017.pdf
solo utenti autorizzati
Dimensione
1.26 MB
Formato
Adobe PDF
|
1.26 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.