Building logistic models by means of a non parametric goodness of fit test: a case study
作者： S. Cessie , J. C. Houwelingen
DOI: 10.1111/J.1467-9574.1993.TB01410.X
关键词: Statistic 、 Econometrics 、 Statistics 、 F-test 、 PRESS statistic 、 Mathematics 、 Goodness of fit 、 Likelihood-ratio test 、 Ancillary statistic 、 Pearson's chi-squared test 、 Test statistic
摘要: A sequence of logistic models is fitted to data from a Dutch follow-up study on preterm infants (POPS). To examine the adequacy model, recently developed non parametric method check goodness fit applied (le Cessie and Van Houwelingen (1991)). This uses test statistic based upon kernel regression methods. In this paper problem choosing “best” bandwidth, corresponding greatest power statistic, avoided by computing for range different bandwidths. Testing then asymptotic distribution maximum statistics. The testing used as criterion, contribution each individual observation diagnostic tool localize deviations determine directions in which model can be improved.
sci-hub.se 参考文章(5)
E. A. Nadaraya, On Estimating Regression Theory of Probability and Its Applications. ,vol. 9, pp. 141- 142 ,(1964) , 10.1137/1109020
Charles C. Brown, On a goodness of fit test for the logistic model based on score statistics Communications in Statistics-theory and Methods. ,vol. 11, pp. 1087- 1105 ,(1982) , 10.1080/03610928208828295
David W. Hosmer, Stanley Lemesbow, Goodness of fit tests for the multiple logistic regression model Communications in Statistics-theory and Methods. ,vol. 9, pp. 1043- 1069 ,(1980) , 10.1080/03610928008827941
A. AZZALINI, A. W. BOWMAN, W. HÄRDLE, On the use of nonparametric regression for model checking Biometrika. ,vol. 76, pp. 1- 11 ,(1989) , 10.1093/BIOMET/76.1.1
S. le Cessie, J. C. van Houwelingen, A goodness-of-fit test for binary regression models, based on smoothing methods Biometrics. ,vol. 47, pp. 1267- 1282 ,(1991) , 10.2307/2532385