Psychometrics is a field within psychology that is loosely defined as the study of advancing quantitative measurement in behavioral sciences. It was first defined in 1879 by Sir Francis Galton, a Victorian era statistician, sociologist, psychologist, anthropologist, and psychometrician, among other fields, as “the art of imposing measurement and number upon operations of the mind.” Statistics is prominent within psychometrics due to the fact that most psychological measurements are conducted through tests and questionnaires. One psychometrician, Henk Kelderman, from Leiden University in Amsterdam, elaborated on this when he said, “Psychometrics covers virtually all statistical methods that are useful for the behavioral and social sciences including the handling of missing data, the combination of prior information with measured data, measurement obtained from special experiments, visualization of statistical outcomes, measurement that guarantees personal privacy, and so on.” The field of psychometrics is currently referred to as quantitative psychology.
Common tests that are studied by practitioners of psychometrics include intelligence tests, personality and behavior tests, and tests that analyze our attitudes and beliefs. Test results are then analyzed by psychometricians to see how they are designed, delivered, and interpreted. These results are then investigated to see how they can be applied to research conducted by health and organizational researchers. Health researchers may use psychometric testing to create methodology that examines pain, fatigue, distress, anxiety, alertness, mobility, and agility. Organizational researchers may apply psychometric testing to create assessments that analyze job satisfaction, perceived job characteristics, commitment to the organization, work-related stress, job roles, work-life balance, leadership styles, and how much of a fit a person is to an organization.
To analyze these tests requires the use of math and statistics and the feedback of individuals who respond to the given measures so that psychometricians can see whether the measures worked the way that they were meant to work. Questions in measures should not be repetitive and should cover varying perspectives so that enough detail is gathered from the given measures. What practitioners of psychometrics are investigating is whether the results are valid, reliable, and responsive.
Examining validity entails looking for evidence that shows that the test measures what it is intended to. A measure could be considered invalid if aspects of a questionnaire are not included. An example of validity in a measure is when a questionnaire is given asking whether physical activity is important to those who are taking the questionnaire. It would be considered a valid assessment if individuals who state that physical activity is important exercise more than those who felt that physical exercise did not matter.
Reliability assesses whether individuals give consistent answers to questions when others are given the questionnaire under similar circumstances. One example of reliability is assessing difficulties when commuting. Statistical analysis would determine if those given the measure on different occasions would produce the same results. Measures are considered reliable when different individuals give similar responses and score similarly.
Responsiveness examines whether the test leads to meaningful change such as if a person’s situation, skills, or beliefs changed as a result of a given measure. An example is seeing if the tool used is able to detect a change in the test subject and how much change has to occur before it is detected by the assessment. Responsiveness could be applied when workplaces test wellness programs to evaluate their effectiveness. It would be considered responsive if the effects capture change.