Minimum Distance Estimation in a Linear Regression Model
Koul, H. ; DeWet, T.
Ann. Statist., Tome 11 (1983) no. 1, p. 921-932 / Harvested from Project Euclid
This paper discusses a class of minimum distance Cramer-Von Mises type estimators of the slope parameter in a linear regression model. These estimators are obtained by minimizing an integral of squared difference between weighted empiricals of the residuals and their expectations with respect to a large class of integrating measures. The estimator corresponding to the weights proportional to the design variable is shown to be asymptotically efficient within the class at a given error distribution. The paper also discusses the asymptotic null distribution of a class of minimum Cramer-Von Mises type goodness-of-fit test statistics.
Publié le : 1983-09-14
Classification:  Weighted empiricals,  goodness-of-fit tests,  efficient estimators,  62F10,  62J05,  62F03
@article{1176346258,
     author = {Koul, H. and DeWet, T.},
     title = {Minimum Distance Estimation in a Linear Regression Model},
     journal = {Ann. Statist.},
     volume = {11},
     number = {1},
     year = {1983},
     pages = { 921-932},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176346258}
}
Koul, H.; DeWet, T. Minimum Distance Estimation in a Linear Regression Model. Ann. Statist., Tome 11 (1983) no. 1, pp.  921-932. http://gdmltest.u-ga.fr/item/1176346258/