ERIC Number: ED199269
Record Type: RIE
Publication Date: 1980-Apr
Reference Count: 0
Canonical Correlation: Recent Extensions for Modelling Educational Processes.
Canonical correlation (CC) analysis is discussed with a view toward providing an intuitive understanding of how the technique operates. CC analysis entails calculation of one or more sets of canonical variate coefficients (CVC), i.e., weights which can be applied to the variables in a study. A canonical function (CF) always consists of exactly two canonical variates calculated so that the product-moment correlation between them is maximized. Thus, a squared CC coefficient indicates the proportion of variance shared by two sets of variables which each have been weighted by variate coefficients so that the CC will be as large as possible. The number of CFs which can be derived for a given data set is equal to the number of variables in the smaller of the two variable sets. CC analysis actually involves analysis of a matrix which is computed from the inter-variable correlation matrix and is appropriately applied when three assumptions are met. These assumptions are discussed, an heuristic application of CC analysis is used to clarify how the procedure operates, and four additional coefficients which greatly aide interpretation efforts are defined. Interpreting canonical results is discussed from each of three levels of specificity. (RL)
Publication Type: Speeches/Meeting Papers; Reports - Descriptive
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the American Educational Research Association (64th, Boston, MA, April 7-11, 1980).