Mrs. Cho is careful to make sure that she fairly represents the whole year’s work on the final exam for her American literature class. If Mrs. Cho achieves this goal, her test will have

(C) content validity.

Mrs. Cho is concerned about the content validity of her test. A test that fairly represents all the material taught in her class has content validity. Validity, in general, measures how well a test measures what it is supposed to measure. In order for Mrs. Cho’s test to have construct validity, we would need to know that the test was successful in differentiating between varying levels of achievement in Mrs. Cho’s class. If the test has criterion validity, we would have to know that the test successfully identified either those students who had excelled in their study of American literature (concurrent validity) or those students who would excel in the future (predictive validity). Reliability is a measure of how consistent the scores are on a test. Test-retest reliability involves giving the same test to the same population on at least two different occasions and measuring the correlation between the sets of scores. Split-half reliability is when one test is divided into two parts and the correlation between people’s scores on the two halves is measured.