Métodos de diagnóstico em modelos logísticos trinomiais

作者: Jose Alberto Pereira da Silva

DOI: 10.11606/D.45.2003.TDE-26112008-160411

关键词:

摘要: The trinomial logistic models can be interpreted as a natural extension of the traditional binomial model to situations in which response allows only three possible results. We first introduce and then some inferential aspects, such estimation hypothesis testing are discussed. Goodness-of-fit measures also given. However, aim this work is presentation diagnostic procedures for models. show that methods developed adapted straightforward development direct methods, even though possible, general requires more complex calculation. Some these evaluation residuals, high leverage points, deletion local influence presented. Comparisons between made via examples with real data.

参考文章(49)
D. R. Cox, E. J. Snell, A General Definition of Residuals Journal of the Royal Statistical Society: Series B (Methodological). ,vol. 30, pp. 248- 265 ,(1968) , 10.1111/J.2517-6161.1968.TB00724.X
Peter McCullagh, John Ashworth Nelder, Generalized Linear Models ,(1983)
Wing-Kam Fung, Unmasking Outliers and Leverage Points: A Confirmation Journal of the American Statistical Association. ,vol. 88, pp. 515- 519 ,(1993) , 10.1080/01621459.1993.10476302
Manuel Galea, Gilberto A. Paula, Heleno Bolfarine, Local influence in elliptical linear regression models The Statistician. ,vol. 46, pp. 71- 79 ,(1997) , 10.1111/1467-9884.00060
Stanley Lemeshow, David W. Hosmer, Applied Logistic Regression ,(1989)
David Collett, Modelling Binary Data ,(1991)
Samprit Chatterjee, Ali S. Hadi, Influential Observations, High Leverage Points, and Outliers in Linear Regression Statistical Science. ,vol. 1, pp. 379- 393 ,(1986) , 10.1214/SS/1177013622
David C. Hoaglin, Roy E. Welsch, The Hat Matrix in Regression and ANOVA The American Statistician. ,vol. 32, pp. 17- 22 ,(1978) , 10.1080/00031305.1978.10479237
R. Dennis Cook, Daniel Peña, Sanford Weisberg, The likelihood displacement: A unifying principle for influence measures Communications in Statistics-theory and Methods. ,vol. 17, pp. 623- 640 ,(1988) , 10.1080/03610928808829645