Review questions

1. What two approaches have traditionally been used to study the validity of Criterion-referenced tests?

2. What are the theoretical arguments and expert judgments approaches to content validity? And, how can they be combined?

3. What are construct validity intervention studies, differential groups studies, and hierarchical-structure studies? And, how can they be combined with each other and with content validity arguments?

4. What is Messick’s (1988) expanded view of validity? What are the evidential and consequential bases of test interpretation and use? And, how are they interrelated?

5. How are Cronbach’s (1988) questions about the functional, political, economic, and explanatory perspectives on testing related to test validity?

6. Are the use of traditional cut-points and grading on a curve valid decision making strategies? Is the use of cut-points necessarily arbitrary?

7. What is standards setting? And, what are the similarities and differences between the available alternative approaches like state mastery approaches, continuum approaches, test-centered approaches, and student-centered approaches?

8. What is the relationship between standards setting and Criterion-referenced decision making?

9. What is the relationship between standards and dependability?

10. What is the relationship between validity and Criterion-referenced decision making?