The Choice of Variables for Prediction in Curvilinear Multiple Regression
Brooks, R. J.
Ann. Statist., Tome 1 (1973) no. 2, p. 506-516 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
A Bayesian formulation of the problem of analysing data from a curvilinear regression of $y$ on $x_1, x_2, \cdots, x_r$ in order to predict a future value of $y$ is considered. The problem is to obtain a criterion to decide which is the best subset of $x_1, x_2, \cdots, x_r$ to perform this prediction. Under very strict assumptions the criterion obtained is shown to use the same statistic as the orthodox (least squares) approach.
Publié le : 1973-05-14
Classification:  
@article{1176342416,
     author = {Brooks, R. J.},
     title = {The Choice of Variables for Prediction in Curvilinear Multiple Regression},
     journal = {Ann. Statist.},
     volume = {1},
     number = {2},
     year = {1973},
     pages = { 506-516},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176342416}
}

Brooks, R. J. The Choice of Variables for Prediction in Curvilinear Multiple Regression. Ann. Statist., Tome 1 (1973) no. 2, pp.  506-516. http://gdmltest.u-ga.fr/item/1176342416/