In general, the greater the correlation of a given predictor with other predictors of a criterion, the more useful the predictor will be.

Question

Quizplus · Accepted Answer

When predictors are highly correlated with each other, it indicates that they are measuring similar things and redundancy may occur. This can lead to multicollinearity issues in regression models and decrease the usefulness of the predictors. Therefore, it is generally more useful to have predictors that are moderately correlated with each other, but highly correlated with the criterion variable.

In General, the Greater the Correlation of a Given Predictor