Measurement in Practice
The use of scales in social sciences has been considered an important element in the development of ideas. Indeed, many common diagnoses in the mental health field have been aided by some very distinct and robust measures (e.g., the CIDI (Andrews & Peters, 1998) and the Beck Depression inventories (Beck, 2006)). The now-famous concepts and ideas such as social distance (Bogardus, 1933) and anomie (Srole, 1956) all find support on well-established social scales. Still others such as the BEM Sex Inventory (Bem, 1974), the Kansas Marital Satisfaction (Schumm, 2001), or Herek (1984) scale on attitudes toward lesbians and gays all share one very important trait—good design and methodological sophistication. This is not to say that each measure is without error, clearly they are not, but it is to say that the developmental approaches used by the authors reflected a level of concern and sophistication that renders these scales as useful and adaptable measures across a variety of subjects and in numerous cultural settings. With some important modifications, these instruments endure. In short, these measures meet the criteria of scale construction by providing a concrete measurement of abstract theoretical ideas. The questions then become, what are scales, how are they composed, why do they work, and how can one be sure that the scale is really an appropriate measure of the theoretical construct under examination? Throughout this book, these issues will be addressed in great detail. The purpose of this chapter is to provide some insight into these issues and offer an overview of the process. Let me begin with a very critical caveat—No scale is without its problems and not all elements can be combined to make a scale no matter the reliability score. Good research methodology along with logic and good sense must always accompany any measure worth its weight.