chapter 6: Measurement
1. The difference between reliability and validity of a measure. Example.
They are all important qualities of measurement. Reliability means the degree to which a measure yields consistent results. Eg: Using a scale to measure a rock’s weight, the scale would tell its weight with reasonably reliable measurements whenever it measures. Validity means the degree to which a measure taps what we think it’s measuring. Eg: Like measuring the rock’s weight, no matter how valid the scale is when measuring the weight, it can’t validly measure its shape or texture.
2. What several types of validity mean. Difference between face and predictive validity.
Face validity(表面效度): a test for validity that involves the judgment of everyday people, like you and me. The answer to the question, “How old are you?” seems like a pretty good measure of age and, therefore, has high face validity. On the other hand, the question, “In your opinion, what is the proper role of the military in foreign affairs?” would yield a poor measure of age and, therefore, has low face validity.
Content validity(内容效度)：a test for validity that involves the judgment of experts in a field. It’s similar to face validity, except that it generally involves the assessment of experts in a field, rather than just regular people.
Predictive validity(预测效度): a method that involves establishing how well the measure predicts future behaviors you’d expect it to be associated with. It is different from face validity and content validity, because it doesn’t directly involve the judgment of people about the measure. Predictive validity involves establishing how well the measure predicts future behaviors you’d expect it to be associated with.
Concurrent criterion validity(准则效度): how well a measure is associated with behaviors it should be associated at the present time.
The distinguishing characteristic of predictive and concurrent validity is that