If a test is going to predict a criterion well, the correlation between the test and the criterion should be
A) around .00 to indicate no errors of estimate.
B) a large, positive coefficient of correlation.
C) either a large positive or large negative correlation.
D) a large, negative coefficient of correlation.

Question

Quizplus · Accepted Answer

A high correlation between a test and a criterion, whether positive or negative, indicates that the test predicts the criterion well. A positive correlation means that as test scores increase, criterion measures increase, while a negative correlation means that as test scores increase, criterion measures decrease. Both scenarios indicate predictive validity.

If a Test Is Going to Predict a Criterion Well