Scientists and clinicians use measurement as a way of understanding, evaluating, and differentiating characteristics of people, objects, and systems. Measurement provides a mechanism for achieving a degree of precision in this understanding so that we can describe physical or behavioral characteristics according to their quantity, degree, capacity, or quality. This allows us to communicate in objective terms, giving us a common sense of “how much” or “how little” without ambiguous interpretation. There are virtually no clinical decisions or actions that are independent of some type of measurement.
The purpose of this chapter is to explore principles of measurement as they are applied to clinical research and evidence-based practice (EBP). Discussion will focus on several aspects of measurement theory and how these relate to quantitative assessment, analysis, and interpretation of clinical variables.
We use measurement as a basis for making decisions or drawing conclusions in several ways:
Describing quantity of an existing variable to determine its value.
Making decisions based on a criterion or standard of performance.
Drawing comparisons to choose between courses of action.
Evaluating responses to assess a patient’s condition by documenting change or progress.
Discriminating among individuals who present different profiles related to their conditions or characteristics.
Predicting outcomes to draw conclusions about relationships and consider expected responses.
“Measurement” has been defined as:
The process of assigning numerals to variables to represent quantities of characteristics according to certain rules.1
Let us explore the three essential elements of this definition.
Quantification and Measurement
The first part of the definition of measurement emphasizes the process of assigning numerals to variables. A variable is a property that can differentiate individuals or objects. It represents an attribute that can have more than one value. Value can denote quantity (such as age or blood pressure) or an attribute (such as sex or geographic region).
Numerals are used as labels, with no quantitative meaning, such as coding data on an opinion scale from “1” Strongly Disagree to “5” Strongly Agree. When the variable can take on only two values, such as using “0” to represent “No” and a “1” to represent “Yes” on a survey question, the measure is considered dichotomous. Variables that can have multiple values, such as a five-point opinion scale, are called polytomous.
A number represents a known quantity of a variable. Accordingly, quantitative variables can be operationalized and assigned values, independent of historical, cultural, or social contexts within which performance is observed. Numbers can take on different kinds of values.
A continuous variable can theoretically take on any value along a continuum within a defined range. Between any two integer values, an indefinitely large ...