Registro Completo |
Biblioteca(s): |
Embrapa Unidades Centrais. |
Data corrente: |
23/10/2003 |
Data da última atualização: |
12/04/2004 |
Autoria: |
ARELLANO-VALLE, R. B.; OZAN, S.; BOLFARINE, H.; LACHOS, V. H. |
Título: |
Skew normal measurement error models. |
Ano de publicação: |
2003 |
Fonte/Imprenta: |
São Paulo,SP: USP-IME, 2003. |
Páginas: |
21 p. |
Série: |
(Relatório Técnico, RT-MAE 2003-10). |
Idioma: |
Inglês |
Conteúdo: |
In this paper we define a class of skew normal measurement error models, extending usual symmetric normal in order to avoid data transformation. The likelihood function of the observed data is obtained, which can be maximized by using existing statistical software. Inference on the parameters of interest can be approached by using the observed information matrix, which can also be computed by using existing statistical software, such as the Ox program. Bayesian inference is also discussed for the family of asymmetric models in terms of invariance with respect to the symmetric normal distribution showng that early results obtained for the normal distribution also hosds for the asymmetric family. Results of a simulation study and an analysis of a real data set analysis are provided. |
Palavras-Chave: |
Invariance; Maximum likelihood; Posterior distribution; Prior distribution; Structural model. |
Categoria do assunto: |
-- |
Marc: |
LEADER 01399nam a2200229 a 4500 001 1109141 005 2004-04-12 008 2003 bl uuuu u0uu1 u #d 100 1 $aARELLANO-VALLE, R. B. 245 $aSkew normal measurement error models. 260 $aSão Paulo,SP: USP-IME$c2003 300 $a21 p. 490 $a(Relatório Técnico, RT-MAE 2003-10). 520 $aIn this paper we define a class of skew normal measurement error models, extending usual symmetric normal in order to avoid data transformation. The likelihood function of the observed data is obtained, which can be maximized by using existing statistical software. Inference on the parameters of interest can be approached by using the observed information matrix, which can also be computed by using existing statistical software, such as the Ox program. Bayesian inference is also discussed for the family of asymmetric models in terms of invariance with respect to the symmetric normal distribution showng that early results obtained for the normal distribution also hosds for the asymmetric family. Results of a simulation study and an analysis of a real data set analysis are provided. 653 $aInvariance 653 $aMaximum likelihood 653 $aPosterior distribution 653 $aPrior distribution 653 $aStructural model 700 1 $aOZAN, S. 700 1 $aBOLFARINE, H. 700 1 $aLACHOS, V. H.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Unidades Centrais (AI-SEDE) |
|