Comments on "A general canonical correlation index."

Abstract

The general canonical correlation index (/?».«*) proposed by Stewart and Love is examined. The index does not fulfill either claim made of it by Stewart and Love: (a) It does not represent a proportion of overlapping, or redundant, variance since the index includes an improper term for the variance of a canonical variate and (6) it is not equal to the average of the squared multiple correlations between a linear composite of one set of variables and the elements of a second set, nor is it equal to the average of the squared multiple correlations between a linear composite of one variable set and the canonical variates of a second set.

An exploratory study of the interaction between personality and psychopathology

“…It first was conjectured that Rozeboom's (1965) index of between-set correlation, Rxy, would be nonzero, which would indicate overlap or interaction of the personality trait and psychopathology measures for the abnormal Ss. Because we were aware that this type of analysis is controversial (Miller, 1975;Nicewander & Wood, 1974, 1975Stewart & Love, 1968), it was hypothesized further that the number of significant canonical variates would be greater than unity, which would indicate multidimensionality of the personality trait-psychopathology domain shared variance pattern.…”

A Reply to Karpman

“…His point that redundancy indexes are not symmetrical across batteries is an important one. The fact that the procedure is relatively new (Stewart & Love, 1968) and has been criticized (Nicewander & Wood, 1974) may suggest some caution with the use of the redundancy index. Proponents suggest that, when the redundancy index is low and when the canonical correlation is high, the value of using the index is especially apparent.…”

Strategies in Canonical Correlation with Application to Behavioral Data

“…Even though a canonical variate pair may not extract significant variance from their respective sets a significant canonical correlation may obtain. However, this paper will not explore this index further since the index appears to include an improper term for the variance of a canonical variate (Nicewander and Wood, 1974).…”