RT info:eu-repo/semantics/preprint
T1 Exploring the number of groups in robust model-based clustering
A1 García Escudero, Luis Ángel
A1 Gordaliza Ramos, Alfonso
A1 Matrán Bea, Carlos
A1 Mayo Iscar, Agustín
A2 Universidad de Valladolid
K1 Estadística
AB Two key questions in Clustering problems are how to determine the number ofgroups properly and measure the strength of group-assignments. These questions arespecially involved when the presence of certain fraction of outlying data is also expected.Any answer to these two key questions should depend on the assumed probabilistic-model, the allowed group scatters and what we understand by noise. With this inmind, some exploratory \trimming-based" tools are presented in this work togetherwith their justi cations. The monitoring of optimal values reached when solving arobust clustering criteria and the use of some "discriminant" factors are the basis for these exploratory tools.
YR 2011
FD 2011
LK http://uvadoc.uva.es/handle/10324/5967
UL http://uvadoc.uva.es/handle/10324/5967
LA spa
NO García-Escudero, L.A.; Gordaliza, A.; Matrán, C. y Mayo-Iscar, A. (2011) "Exploring the number of groups in robust model-based clustering". Statistics and Computing Vol. 21, Pag. 585-599
NO Producción Científica
NO Estadística e IO
DS UVaDOC
RD 19-abr-2024