Naslov
Link between orthogonal and standard multiple linear regression models

Autori
Šoškić, Milan ; Plavšić, Dejan ; Trinajstić, Nenad

Izvornik
Journal of chemical information and computer sciences (0095-2338) 36 (1996), 4; 829-832

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
multiple linear regression ; dominant component method ; orthogonalization

Sažetak
Several topics in connection with a recently proposed method for the orthogonalization of predictor variables (dominant component analysis) are considered. Applying the sequential regression procedure, it is shown that dominant component analysis and the standard multiple linear regression method are directly related to each other. In addition, it is demonstrated that an earlier proposed iterative procedure for the orthogonalization of a correlated variable can be efficiently replaced by one step regression. It is also shown that the coefficient of determination for an orthogonal descriptor coincides with the corresponding squared semipartial correlation coefficient. Finally, the origin of extra information in an orthogonalized predictor variable is discussed.

Izvorni jezik
Engleski

Znanstvena područja
Kemija

POVEZANOST RADA