Educational Measurement, Instrumentation, and Assessment

The foundation of quality quantitative educational research is predicated on the quality of the data sources used to answer our research questions. As such, the principle of “garbage in, garbage out” is of utmost concern in the design and selection of measurement instruments to operationalize and measure our constructs of interest with our target populations. This chapter provides a brief overview of educational measurement concepts and concerns pertinent to educational researchers. First, the chapter explores the established levels of measurement outlined by Stevens (1946): 1) nominal, 2) ordinal, 3) interval, and 4) ratio. Next, the chapter explores two critical properties of educational tests and scales used to inform educational research and evaluation: 1) validity, and 2) reliability. The chapter outlines the different types of validity evidence and methods for providing evidence for your measurement systems. Reliability is defined, and several established methods for generating reliability evidence are discussed. The chapter provides the most commonly used quantitative data sources and instruments, including tests and scales, questionnaires, observation protocols, and log trace data. The chapter also comments on the process for selecting or creating different measurement instruments.