Chi siamo   |   Guida alla creazione di un record   |   Help   |   FAQ diritto d'autore   |   Tesi di dottorato   |   Università Bicocca   |   Biblioteca

BOA Bicocca Open Archive >
Pubblicazioni >
03 - Contributo in libro >

Please use this identifier to cite or link to this item:http://hdl.handle.net/10281/33569

Authors: Greselin, F; Punzo, A
Title: Closed Likelihood-Ratio Testing Procedures to Assess Similarity of Covariance Matrices
English abstract: Different degrees of similarity can be devised among the k covariance matrices Σh, referred to k groups, under the assumption of multivariate normality, using their spectral decomposition. In this paper we introduce a closed testing procedure allowing for a choice between eight patterns of covariances. The new methodology allows to disclose a richer information on the data underlying structure than the classical existing methods, and also a more parsimonious parameterization. An application on a real data set exemplify the proposal and shows its performances.
Keywords: Eigenvalue Decomposition, Proportional Covariance Matrices, Com- mon Principal Components, Closed Testing Procedures, Likelihood-Ratio Tests.
MIUR Subject : Settore SECS-S/01 - Statistica
ISO Language : eng
???metadata.dc.date.accepted???: 15-Apr-2012
Issue Date: 2012-06-01
Format: Online
Referee: Esperti anonimi
Circulation: Rilevanza internazionale
Type: Capitolo o saggio
URL: http://meetings.sis-statistica.org/index.php/sm/sm2012/paper/viewFile/2264/72
Is a new version of: http://hdl.handle.net/10281/29233
Citation: Greselin, F., & Punzo, A. (2012). Closed Likelihood-Ratio Testing Procedures to Assess Similarity of Covariance Matrices. In Atti della 46TH SCIENTIFIC MEETING OF THE ITALIAN STATISTICAL SOCIETY. Nicola Torelli.
Appears in Collections:Pubblicazioni >03 - Contributo in libro
DIPARTIMENTO DI STATISTICA E METODI QUANTITATIVI >03 - Contributo in libro

Files in This Item:

There are no files associated with this item.


SFX Query


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.




 

Support, maintenance, development and hosting provided by AePIC team @ CILEA - Powered by DSpace Software