Component Loadings
The following figure shows the plot of component loadings for the survey data. When there are no missing data, the component loadings are equivalent to the Pearson correlations between the quantified variables and the object scores.
The distance from the origin to each variable point approximates the importance of that variable. The canonical variables are not plotted but can be represented by horizontal and vertical lines drawn through the origin.
The relationships between variables are apparent. There are two directions that do not coincide with the horizontal and vertical axes. One direction is determined by Age in years, Newspaper read most often, and Neighborhood preference. The other direction is defined by the variables Marital status, Music preferred, and Pets owned. The Pets owned variable is a multiple nominal variable, so there are two points plotted for it. Each quantification is interpreted as a single variable.