Psychometrics has evolved as a subfield of psychology to become the science of measurement of unobservable individual characteristics.
Psychometrics has evolved as a subfield of psychology to become the science of measurement of unobservable individual characteristics.
Unlike psychophysics which mostly focus on perceptual attributes, psychometrics aims at providing reproducible methods for assessing high-level or cognitive skills through the scientific development and evaluation of reliable and valid mental tests or questionnaires. Common traits of interest are knowledge, attitudes, personality, and abilities. Psychometric techniques developed for assessing intelligence or proficiency are now used in political science, social sciences, or health surveys. The Psychometrika journal certainly reflects the current state of the art in this field, but other reviews now offer well-acknowledged articles on multivariate/multilevel data analysis, structural equation, or other latent variable models. Recommended books are Nunally and Bernstein (1994), Kline (1998), Boomsma et al. (2001), De Boeck and Wilson (2004), Skrondal and Rabe-Hesketh (2004), and Rao and Sinharay (2007).
Many R packages provide dedicated functions for applied psychometrics and item analysis, including exploratory and confirmatory factor analysis, multidimensional scaling, and other methods belonging to Classical Test Theory, Item Response Theory, and Structural Equation Modeling (See the Psychometrics task view and the Journal of Statistical Software). For Matlab users, there is the IRTm toolbox. For Stata users, there are gllamm and raschtest, among others (Check out the FreeIRT project).
