Search Results

This chapter explores measurement ‘from above’: that is, looking for a view that we can have after the measurement procedures, concepts, and theories have stabilized. This resting point in the conceptual and scientific development is fleeting and momentary — yet marking a context in which some things can be taken for granted pro tem, where it makes sense to ask about the world-picture of currently accepted physical theory. The physical conditions of possibility for measurement, the general theory of measurement, and what cannot count as measurement in a theoretical context are discussed, drawing on general lessons derived from 20th-century foundations of physics.

Unobservable characters called constructs or latent traits are frequently measured by social scientists though certain educational and psychological tests. It is observed in this chapter that measuring the observable characteristics is not as deterministic as measuring physical characteristics and that measurement error exists. In this first chapter, general concepts are presented. Reliability is defined as “the extent to which test scores are consistent with another set of test scores produced from a similar process.” The measurement procedure includes all aspects of testing the situation. Sampling can be done by the sampling of one or more aspects of the measurement procedure or the sampling of examinees. The classical test theory and the generalizability theory are also presented. Concepts under reliability are discussed in more detail in the succeeding chapters.

Assumptions about a measurement procedure can be categorized into three divisions, namely, assumptions about dimensionality, error score correlations, and the nature of measurement procedure replications. In this chapter, each of these categorized is discussed in detail. A discussion of the consequences for violating these assumptions is also provided. Dimensionality pertains to the number of factors underlying scores produced from a measurement procedure. Assumptions are presented for dimensionality. A violation occurs when reliability is underestimated when scores are not unidimensional. Error score correlations could be associated with dimensionality. A violation is when internal consistency estimates of reliability are inflated in the presence of positively correlated errors. Finally, the chapter looks at the nature of measurement procedure replications. Assumptions and violations are presented as well.