Test Construction

Question 1

Validity

Answer 1

meaningfulness, usefulness, accuracy
either tells us how well the test is measuring what it’s supposed to be measuring (typically content or construct validity) or how well the test can be used to infer criterion performance (criterion-related validity)

Question 2

content validity

Answer 2

no numerical validity coefficient
how adequately a test samples a particular content area
quantified by asking a panel of experts if each item is essential, useful/not essential, or not necessary

Question 3

criterion-related validity

Answer 3

looks at how adequately a test score can be used to infer, predict, or estimate a criterion outcome (e.g. how well do SAT scores predict college GPA)
calculated using Pearson r to correlate test scores (predictor scores) with criterion scores (outcome scores)
validities as low as .20 considered acceptable

Question 4

2 types of criterion-related validity

Answer 4

concurrent validity and predictive validity

Question 5

concurrent validity

Answer 5

predictor and criterion are measured at the same time and correlated at about the same time

Question 6

predictive validity

Answer 6

delay between measurement of predictor and the criterion