The Imperative Of Evaluating Psychometric Properties Of Scales For Accurate Measurement: A Review

Abstract

Scale development and validation represent fundamental processes in various disciplines within health, social, and behavioral sciences. However, the methodologies involved can be complex, laden with specialized terminology, unfamiliar to many, and demanding in terms of resources. Moreover, these processes are often not adequately covered in graduate education. Therefore, our aim was to succinctly outline the procedures of scale development in a clear manner, with the dual objectives of facilitating the creation of new, valid, and reliable scales, and enhancing the quality of existing ones. To achieve this, we have compiled a guide outlining best practices for developing scales to measure intricate phenomena. This guide is not a comprehensive systematic review but rather a synthesis of technical literature and insights gleaned from our extensive experience in developing or adapting various scales over several decades. We have identified three overarching phases encompassing nine specific steps. The initial phase involves generating items and assessing their content validity. Subsequently, in the scale construction phase, activities include pre-testing questions, survey administration, item reduction, and determining the scale's dimensionality. Finally, in the scale evaluation phase, dimensionality and reliability testing, as well as validity assessment, are conducted. Throughout the guide, we have incorporated illustrative examples of best practices for each step. In summary, this primer aims to empower both researchers and practitioners to comprehend the conceptual and methodological aspects of scale development and validation, thereby fostering advancements in our understanding of various health, social, and behavioral outcomes.