It is suggested that, for a given column of a correlation matrix, the highest squared off-diagonal element in that column be taken as an initial approximation to that attribute's communality, for all attributes, in iterative methods of factoring.
Get full access to this article
View all access options for this article.
References
1.
GuttmanL. (1940) Multiple rectilinear prediction and the resolution into components. Psychometrika, 5, 75–99.
2.
KaiserH. F. (1990) On Guttman's proof that squared multiple correlations are lower bounds for communalities. Perceptual and Motor Skills, 1990, 71, 1004–1006.
3.
TuckerL. R.CooperL. G.MeredithW. M. (1972) Obtaining squared multiple correlations from a correlation matrix which may be singular. Psycbometrika, 37, 143–148.
