This paper provides a tree-based methodology to deal with three-way data sets. The aim is to partition cases on the basis of a set of attributes measured in various situations. A supervised approach is considered, thus the recursive partitioning criterion takes account of the internal homogeneity of the response variable. The proposed classification and regression tree-based methodology can be extended to multivariate response variables as well. In the following, the general framework is introduced and some special cases are briefly described. The results of an application on a real data set are summarized.
3Way Trees / Siciliano, Roberta; Tutore, VALERIO ANIELLO; Aria, Massimo. - STAMPA. - 1:(2007), pp. 231-234. (Intervento presentato al convegno Meeting of Classification and Data Analysis Group 2007 tenutosi a Macerata nel 12-14 settembre).
3Way Trees.
SICILIANO, ROBERTA;TUTORE, VALERIO ANIELLO;ARIA, MASSIMO
2007
Abstract
This paper provides a tree-based methodology to deal with three-way data sets. The aim is to partition cases on the basis of a set of attributes measured in various situations. A supervised approach is considered, thus the recursive partitioning criterion takes account of the internal homogeneity of the response variable. The proposed classification and regression tree-based methodology can be extended to multivariate response variables as well. In the following, the general framework is introduced and some special cases are briefly described. The results of an application on a real data set are summarized.| File | Dimensione | Formato | |
|---|---|---|---|
|
Paper ufficiale da sito springer.pdf
non disponibili
Tipologia:
Documento in Post-print
Licenza:
Accesso privato/ristretto
Dimensione
597.14 kB
Formato
Adobe PDF
|
597.14 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
