Classical Test Theory (TCT) first appeared in the 20th century from Spearman’s work, which in a way can be seen as the beginning of psychometrics. Word testing, in this concept, refers to tests designed to evaluate knowledge, skills, or functions. .
In psychology, tests are psychological or psychotechnical tests for studying or evaluating a function, so psychological tests are tools designed to evaluate or measure an individual’s psychological characteristics.
- The tests are sophisticated measuring instruments that.
- In many cases.
- Are of valuable help in psychological evaluation.
- For this the test must meet the minimum psychometric requirements and the specialist who applies it must know the protocol of administration and comply with that.
On the other hand, test theories tell us how we can evaluate the quality of a test, and also, in many cases, how we can debug the instrument to minimize errors. In this sense, perhaps the two most important concepts of classical test theory. are reliability and validity.
Reliability refers to the consistency or stability of measurements when the measurement process is repeated. In the end, we talk about utopia, because in practice it is impossible to reproduce the same conditions in two different measures. It is relatively easy to act on external variables. , such as controlling the existence of a similar temperature or noise level. However, controlling the internal variables of the person performing the test is more complicated. Think of humor, for example.
Validity refers to the degree to which empirical evidence and theory support the interpretation of test results. (2) Otherwise, it could be said that validity is the ability of a measuring instrument to significantly and adequately quantify the characteristic for which the measurement was designed. .
So, there are two main theories about the construction and analysis of tests, the first, which we are talking about, is the classical theory of tests (TCT), the second is the theory of the response to items (IRT). Here are the main aspects of TST.
This approach tends to be the most commonly used in test analysis and construction. A person’s responses to a test are compared using statistical or qualitative methods with responses from others who have completed the same test, allowing a classification to be performed.
However, doing this classification is not so simple. The psychologist, like any other professional, must ensure that the instrument he uses measures accurately, with a small margin of error.
So, when a psychologist tests one or more people, what they get are the empirical scores that person or people get on the test. However, it does not tell us how accurate these scores are; we don’t know whether or not these empirical scores match the scores that actually match that person on the test.
For example, scores may have dropped because the person examined is not feeling well that day or even because the physical conditions in which the test application was developed were not the best.
“Psychologists, such as those who make fuel pumps, are responsible for ensuring that test results are accurate and error-free. “-José Muñiz, 2010-
It was at the beginning of the twentieth century, as we have already said, that Spearman proposed this classic theory of testing, and the researcher created a very simple model for people’s test scores: the classic linear model.
This model assumes that the score obtained by a person in a test, which we call empirical scoring and which is usually referred to by the letter X, consists of two components: the first is the actual score (V) and the actual score (V) the second is error (e). The latter may be due to many causes that we cannot control, so TCT is responsible for the precise determination of the measurement error.
This can be expressed as follows: X – V and
Then, later, Spearman added three hypotheses to the model.
The classic theory of tests is simple, does not require advanced mathematical knowledge to implement it and can be applied in any context, the problem is that the results provided will always be related to the population in which the test was validated. , in many cases, the minimum test required to be considered acceptable is not sufficient.