PSY 370 Lecture Notes - Lecture 36: Assessment Centre, Meta-Analysis, Psy
Document Summary
One validity study does not guarantee your validity coefficient. Test again with a different sample (or the other half of your original sample)--how similar is the validity coefficient. Essentially, the average validity coefficient across several validity studies. Any one study may contain error or situation-specific factors. We can be more confident in the result of a meta-analysis. How confident can we be that our test predicts this across situations. It"s a good idea to have more than one predictor. Remember, our best tests usually predict only about 25% of the variance. We can combine tests or predictors that tap various aspects of our criterion. Good batteries predict better than any individual test or predictor. You use a resume (r = . 10), a personality test (r = . 22), and an assessment center (r = . 25). But it will be more than our best test predictor and probably somewhat less than the sum of all of them together.