ABSTRACT
This chapter offers a non-technical discussion of the concept of reliability intended to complement the presentation in the remaining chapters of this section of a number of theories ofmeasurement applied to testing language proficiency. These models are to an extent related, and reliability is a concept common to them all. This chapter looks at measurement and the limits of the measurement metaphor. Because
these limits impact on the interpretations we can make of test scores, my central concern is with the relationship of reliability and validity. Reliability and validity are classically cited as the two most important properties of a test. When
Bachman (1990) identified four key qualities – validity, reliability, impact and practicality, he was proposing that in any testing situation validity and reliability should be maximised to produce the most useful results for test users, within practical constraints that always exist. As will be further discussed below, reliability and validity have often been portrayed as potentially in conflict. Here, reliability will be presented rather as an integral component of validity, and approaches to estimating reliability as potential sources of evidence for the construct validity of a test.
