ABSTRACT

The usual procedures followed in factor interpretation are very simple. Those data variables with high factor loadings are considered to be “like” the factor in some sense and those with zero or near-zero loadings are treated as being “not like” the factor, whatever it is. Those variables that are “like” the factor, that is, have high loadings on the factor, are examined to find out what they have in common that could be the basis for the factor that has emerged. High loadings in both the positive and negative direction are considered.