Psychological testing
is a field characterized by the use of samples of behavior in order to assess psychological construct(s), such as cognitive and emotional functioning, about a given individual. The technical term for the science behind psychological testing is psychometrics. By samples of behavior, one means observations of an individual performing tasks that have usually been prescribed beforehand, which often means scores on a test. These responses are often compiled into statistical tables that allow the evaluator to compare the behavior of the individual being tested to the responses of a norm group.
A psychological test is an objective and standardized measure of an individual's mental and/or behavioral characteristics. A psychological test is an instrument designed to measure unobserved constructs, also known as latent variables. Psychological tests are typically, but not necessarily, a series of tasks or problems that the respondent has to solve. Psychological tests can strongly resemble questionnaires, which are also designed to measure unobserved constructs, but differ in that psychological tests ask for a respondent's maximum performance whereas a questionnaire asks for the respondent's typical performance.[1] A useful psychological test must be both valid (i.e., there is evidence to support the specified interpretation of the test results[2]) and reliable (i.e., internally consistent or give consistent results over time, across raters, etc.).
It is important that people who are equal on the measured construct also have an equal probability of answering the test items correctly.[3] For example, an item on a mathematics test could be "In a soccer match two players get a red card; how many players are left in the end?"; however, this item also requires knowledge of soccer to be answered correctly, not just mathematical ability. Group membership can also influence the chance of correctly answering items (differential item functioning). Often tests are constructed for a specific population, and this should be taken into account when administering tests. If a test is invariant to some group difference (e.g. gender) in one population (e.g. England) it does not automatically mean that it is also invariant in another population (e.g. Japan).
