In these notes we show that the Pearson residuals (PR) [Lindsay, B.G., 1994. Efficiency versus robustness: the case for minimum Hellinger distance and related methods. Ann. Statist. 22, 1018-1114.] have a natural asymptotic lower bound under the gross error model which can be used in the problem of choosing a root when multiple roots are present in the weighted likelihood estimating equations. Further, we show through an example how the minimum of the PR plays an important role in the robust estimation approach based on weighted likelihood. © 2006 Elsevier B.V. All rights reserved.

Notes on Pearson residuals and weighted likelihood estimating equations / Agostinelli, Claudio. - In: STATISTICS & PROBABILITY LETTERS. - ISSN 0167-7152. - STAMPA. - 76:(2006), pp. 1930-1934. [10.1016/j.spl.2006.04.048]

Notes on Pearson residuals and weighted likelihood estimating equations

Agostinelli, Claudio
2006-01-01

Abstract

In these notes we show that the Pearson residuals (PR) [Lindsay, B.G., 1994. Efficiency versus robustness: the case for minimum Hellinger distance and related methods. Ann. Statist. 22, 1018-1114.] have a natural asymptotic lower bound under the gross error model which can be used in the problem of choosing a root when multiple roots are present in the weighted likelihood estimating equations. Further, we show through an example how the minimum of the PR plays an important role in the robust estimation approach based on weighted likelihood. © 2006 Elsevier B.V. All rights reserved.
2006
Agostinelli, Claudio
Notes on Pearson residuals and weighted likelihood estimating equations / Agostinelli, Claudio. - In: STATISTICS & PROBABILITY LETTERS. - ISSN 0167-7152. - STAMPA. - 76:(2006), pp. 1930-1934. [10.1016/j.spl.2006.04.048]
File in questo prodotto:
File Dimensione Formato  
STAPRO4418.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 177.58 kB
Formato Adobe PDF
177.58 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/112974
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 13
  • ???jsp.display-item.citation.isi??? 12
social impact