You Have Just Designed a New Test of Intelligence, but Apparently

Multiple Choice

You have just designed a new test of intelligence, but apparently it suffers from outcome bias. Which of the following would lead you to this conclusion?

A) Your test underestimates the actual intelligence of your sample.
B) Job performance is more highly correlated with your test for women than for men.
C) Test scores change from one month to the next with the same people.
D) Job performance is negatively correlated with your test scores.
E) Different judges can not agree that the scores reflect actual performance.