RT info:eu-repo/semantics/preprint
T1 A Reweighting Approach to Robust Clustering
A1 Dotto, Francesco
A1 Farcomeni, Alessio
A1 García Escudero, Luis Ángel
A1 Mayo Iscar, Agustín
K1 Estadística
AB An iteratively reweighted approach for robust clustering is presented inthis work. The method is initialized with a very robust clustering partitionbased on an high trimming level. The initial partition is then refinedto reduce the number of wrongly discarded observations and substantiallyincrease efficiency. Simulation studies and real data examples indicate thatthe final clustering solution is both robust and efficient, and naturally adaptsto the true underlying contamination level.
YR 2016
FD 2016
LK http://uvadoc.uva.es/handle/10324/18094
UL http://uvadoc.uva.es/handle/10324/18094
LA spa
DS UVaDOC
RD 19-dic-2024