In the usual linear regression model the sample regression coefficients converge with probability one to the population regression coefficients when the dependent variables are normally distributed and the inverse of the second-order moment matrix of the independent variables converges to the zero matrix.
Publié le : 1976-07-14
Classification:
Least squares estimates,
linear regression,
strong consistency,
62J05,
60F15
@article{1176343552,
author = {Anderson, T. W. and Taylor, John B.},
title = {Strong Consistency of Least Squares Estimates in Normal Linear Regression},
journal = {Ann. Statist.},
volume = {4},
number = {1},
year = {1976},
pages = { 788-790},
language = {en},
url = {http://dml.mathdoc.fr/item/1176343552}
}
Anderson, T. W.; Taylor, John B. Strong Consistency of Least Squares Estimates in Normal Linear Regression. Ann. Statist., Tome 4 (1976) no. 1, pp. 788-790. http://gdmltest.u-ga.fr/item/1176343552/