Explain the process of establishing evidence of validity based on a test’s relationship with constructs, including the various factors that can provide evidence of that validity.
What will be an ideal response?
• The first step in the validation process is establishing a listing of associations the construct has with other constructs.
• Establishing evidence of construct validity for a test involves an ongoing process of gathering evidence that the scores on the test relate to observable behaviors in the ways predicted by the underlying theory and the nomological network.
• If the test is measuring a particular construct, we expect the scores on the test to correlate strongly with scores on other tests that measure the same or similar constructs. This correlation provides us with convergent evidence of validity.
• Just as we would expect some tests to correlate with our new tests, there are other tests we would not expect to correlate with our test. When the test scores do not correlate with unrelated constructs, we can say that the test is demonstrating discriminant evidence of validity.
• Other factors that can provide evidence of construct validity are the test’s reliability, a test’s relationships to a relevant external criteria and the degree to which we can show that a test’s content is a sample of the domain that the test developer intends to measure.
You might also like to view...
________ attempt(s) to close the gap between what is known about optimal health practices and what is actually done
a. Interventions c. Health education b. Medical anthropology d. Intentions
Which of the following may underlie the tendency of children to become attached to inanimate objects, such as blankets or stuffed toys?
a. imprinting b. conditions of worth c. contact comfort d. egocentrism
In general, which of the following is true about anecdotal evidence?
A) It is reliable as long as the facts are correct. B) It takes a long time to collect. C) It is the basis for most scientific conclusions. D) It is poor and unreliable.
If the F ratio from this study is statistically significant, what can you NOT conclude?
A. We could be making Type I Error. B. Basketball players are significantly different from other teams C. The eating habit are different for these sports teams. D. We can conduct a post hoc test.