Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Generalized least squares with misspecified serial correlation structures
Autore:
Koreisha, SG; Fang, Y;
Indirizzi:
Univ Oregon, Charles Lundquist Coll Business, Dept Decis Sci, Eugene, OR 97403 USA Univ Oregon Eugene OR USA 97403 ess, Dept Decis Sci, Eugene, OR 97403 USA
Titolo Testata:
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
, volume: 63, anno: 2001,
parte:, 3
pagine: 515 - 531
SICI:
1369-7412(2001)63:<515:GLSWMS>2.0.ZU;2-W
Fonte:
ISI
Lingua:
ENG
Soggetto:
LINEAR-REGRESSION MODEL; SAMPLE PROPERTIES; ERRORS; ESTIMATORS; EFFICIENCY;
Keywords:
autoregressive disturbances; generalized least squares; incorrect generalized least squares; relative efficiency; serial correlation;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
42
Recensione:
Indirizzi per estratti:
Indirizzo: Koreisha, SG Univ Oregon, Charles Lundquist Coll Business, Dept Decis Sci,Eugene, OR 97403 USA Univ Oregon Eugene OR USA 97403 is Sci, Eugene, OR 97403 USA
Citazione:
S.G. Koreisha e Y. Fang, "Generalized least squares with misspecified serial correlation structures", J ROY STA B, 63, 2001, pp. 515-531

Abstract

The regression literature contains hundreds of studies on serially correlated disturbances. Most of these studies assume that the structure of the error covariance matrix Omega is known or can be estimated consistently from data. Surprisingly, few studies investigate the properties of estimated generalized least squares (GLS) procedures when the structure of Omega is incorrectly identified and the parameters are inefficiently estimated. We compare the finite sample efficiencies of ordinary least squares (OLS), GLS and incorrect GLS (IGLS) estimators. We also prove new theorems establishing theoretical efficiency bounds for IGLS relative to GLS and OLS. Results from an exhaustive simulation study are used to evaluate the finite sample performance and to demonstrate the robustness of IGLS estimates vis-a-vis OLS and GLS estimates constructed for models with known and estimated (but correctly identified) Omega. Some of our conclusions for finite samples differ from established asymptotic results.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 27/09/20 alle ore 13:40:34