Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/20.500.14279/2100
Τίτλος: | Dependence and the dimensionality reduction principle | Συγγραφείς: | Yatracos, Yannis G. | metadata.dc.contributor.other: | Γιατράκος, Γιάννης | Major Field of Science: | Social Sciences | Field Category: | Media and Communications | Λέξεις-κλειδιά: | Mathematical models;Parameter estimation;Statistical methods;Problem solving | Ημερομηνία Έκδοσης: | Ιου-2004 | Πηγή: | Annals of the Institute of Statistical Mathematics, 2004, vol. 56, no. 2, pp. 265-277 | Volume: | 56 | Issue: | 2 | Start page: | 265 | End page: | 277 | Περιοδικό: | Annals of the Institute of Statistical Mathematics | Περίληψη: | Stone's dimensionality reduction principle has been confirmed on several occasions for independent observations. When dependence is expressed with φ-mixing, a minimum distance estimate θ̂n is proposed for a smooth projection pursuit regression-type function θ ∈, that is either additive or multiplicative, in the presence of or without interactions. Upper bounds on the L1-risk and the L 1-error of θ̂n are obtained, under restrictions on the order of decay of the mixing coefficient. The bounds show explicitly the additive effect of φ-mixing on the error, and confirm the dimensionality reduction principle. | URI: | https://hdl.handle.net/20.500.14279/2100 | ISSN: | 15729052 | DOI: | 10.1007/BF02530545 | Rights: | © The Institute of Statistical Mathematics Attribution-NonCommercial-NoDerivs 3.0 United States |
Type: | Article | Affiliation: | National University of Singapore | Affiliation: | National University of Singapore | Publication Type: | Peer Reviewed |
Εμφανίζεται στις συλλογές: | Άρθρα/Articles |
CORE Recommender
Αυτό το τεκμήριο προστατεύεται από άδεια Άδεια Creative Commons