Pseudo-Inverses in the Analysis of Variance
John, Peter W. M.
Ann. Math. Statist., Tome 35 (1964) no. 4, p. 895-896 / Harvested from Project Euclid
The normal equations in the analysis of variance with suitable side conditions give a unique set of estimates, $\tilde\beta_i$, of the parameters $\beta_i$. These estimates are unique linear forms in the actual observations. In the solutions to the normal equations they appear as linear forms in the treatment and block totals; these totals are not independent and so the forms in them are not unique. Thus the normal equations, while giving a unique solution vector, admit an infinite number of pseudo-inverses of the matrix $X' X$. In this paper the relationship between the two most common pseudo-inverses is discussed.
Publié le : 1964-06-14
Classification: 
@article{1177703596,
     author = {John, Peter W. M.},
     title = {Pseudo-Inverses in the Analysis of Variance},
     journal = {Ann. Math. Statist.},
     volume = {35},
     number = {4},
     year = {1964},
     pages = { 895-896},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1177703596}
}
John, Peter W. M. Pseudo-Inverses in the Analysis of Variance. Ann. Math. Statist., Tome 35 (1964) no. 4, pp.  895-896. http://gdmltest.u-ga.fr/item/1177703596/