Regression Systems for Which Optimal Extrapolation Designs Require Exactly $k + 1$ Points
Hoel, Paul G.
Ann. Statist., Tome 9 (1981) no. 1, p. 909-912 / Harvested from Project Euclid
The problem of optimal design for linear regression extrapolation is discussed. A restriction is introduced which will ensure that the number of optimal design points is equal to the number of independent regressors.
Publié le : 1981-07-14
Classification:  Optimal regression designs,  Chebyshev systems,  62K05,  62J05
@article{1176345532,
     author = {Hoel, Paul G.},
     title = {Regression Systems for Which Optimal Extrapolation Designs Require Exactly $k + 1$ Points},
     journal = {Ann. Statist.},
     volume = {9},
     number = {1},
     year = {1981},
     pages = { 909-912},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176345532}
}
Hoel, Paul G. Regression Systems for Which Optimal Extrapolation Designs Require Exactly $k + 1$ Points. Ann. Statist., Tome 9 (1981) no. 1, pp.  909-912. http://gdmltest.u-ga.fr/item/1176345532/