Assessment of Substance Use Disorder

OVERVIEW
This chapter provides an introductory discussion of reliability and validity as they pertain to the provision of rehabilitation and health services. Although the issues are discussed in reference to test use, the concepts and p1inciples are applicable for all forms of data used professionally, including observations and interviews. Keep in mind that reliability and validity are dynamic in nature, evolving with complexity of assessment techniques, the social implications of test data, and statistical advances. Therefore, this chapter offers a broad summary of concepts and techniques, the essentials that rehabilitative clinicians need to know in order to begin their program of study. Interested readers are encouraged to consult the specific professional literature pertaining to their own practice and interests as well as a number of works that are considered “classics” in the field of psychometrics (e.g., Betz & Weiss, 2001; Carroll, 1993; Cronbach, 1988; Cronbach & Meehl, 1955; Gustafsson, 2002; Messick, 1989; Spearman, 1904; Thorndike, 2001; Thurstone, 1925).

LEARNING OBJECTIVES
By the end of the chapter, readers should be able to:
Identify four primary methods used to estimate reliability and give examples of each.
Describe (a) considerations in evaluating reliability estimates, (b) methods to improve reliability, and (c) the impact of floor and ceiling effects on reliability.
Describe four broad approaches used to support the validity of a test and give examples of each.
Distinguish between types of test validity and the evidence for those specific types.
Identify and explain the conditions affecting reliability.
Identify methods test developers may use to improve reliability.
Explain the relationship between validity and reliability.