Premium
The validity of the linear model as a basis for extracting principal components from psychological variables
Author(s) -
Seddon G. M.,
Moore B. G.
Publication year - 1987
Publication title -
british journal of mathematical and statistical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.157
H-Index - 51
eISSN - 2044-8317
pISSN - 0007-1102
DOI - 10.1111/j.2044-8317.1987.tb00876.x
Subject(s) - varimax rotation , principal component analysis , mathematics , linear model , design matrix , basis (linear algebra) , statistics , factor analysis , principal (computer security) , general linear model , econometrics , variables , computer science , psychometrics , geometry , cronbach's alpha , operating system
The investigation was concerned with the principal components analysis of compound variables which do not conform to the linear model. It was conducted using artificial data in which measures on compound variables were derived by multiplying and dividing the scores on the components, rather than adding and subtracting them. The results indicate that using the linear model leads to these variables being resolved just as accurately as variables which do comply with the linear model. However, the correct factor pattern is not always achieved using the Varimax criterion for rotating the principal components.