Evaluation is one of the most important parts of psychological intervention, often conditioned by the results of the administered tests, so the theory of the response to the items (TRI) is one of the theories of measurement of the tests that appear as a complement classical theory of the test.
As mentioned above, the classical theory of tests (TCT) and the IRT could evaluate the same test, each one could establish a relevance or score for each item, in this way it would be possible to obtain a different result for each person. that the IRR would give us a much better calibrated instrument, however, this paradigm is associated with a much higher cost and the participation of specialized professionals.
- The purpose of these two test theories is the same: to generate instruments that measure what we want them to measure with as little error as possible.
- Therefore.
- Psychometry requires some reliability and validity for all tests.
Remember that a test will be more reliable (it will be more reliable) than better to reproduce the results when measuring two subjects?Or the same guy at different times? They have the same level of measurement. On the other hand, validity refers to the extent to which empirical evidence and theory support the interpretation of test results.
Without neglecting its service, the classic approach to test theory has certain limitations, gaps that force us to advance the construction and evaluation of tests.
In TST, the measurements are not invariant compared to the instrument used, so imagine that a psychologist will evaluate the intelligence of three people with a different test for each, in this case the results could not be compared for what?
In fact, each test has its own scale. Thus, in order to compare, for example, the intelligence of a group of people who have been evaluated with different intelligence tests, the scores obtained on other scales would have to be transformed.
In this sense, the IRT allows to compare the results obtained using different instruments on the same scale. In addition, another limitation of the classic approach is the lack of invariance of the properties of the tests with respect to the people used to calculate them. The IRT approach is also responsible for improving this.
To resolve these limitations, the TIR must make stronger and more restrictive assumptions than TST.
The most important assumption of the TRI reports that any measuring instrument must be aligned with an idea, that there is a functional relationship between the values of the variable that measure the items and the probability of combining them. This function is called the item characteristic curve (CCI).
It seems that the item response theory offers a new idea about TST, which is based on the fact that, for example, the most complicated elements of an intelligence test would only be answered by those who are smarter. an item to which all those evaluated would respond in the same way would not have the power to discriminate between more or less intelligent in a subject.
Another hypothesis of the TIR is that most models assume that the elements are of a single dimension, that is, they are one-dimensional. Then, before using the models of this theory, it is necessary to ensure that the data conforms to this one-dimensionality, which implies an important restriction for its use: many instruments used by psychologists do not collect data from a single dimension.
A third hypothesis of the theoretical models of response to the items is local independence, that is, in order to use these models, the elements must be independent of each other, that is, the response to one of them cannot be conditioned on the response given to other elements.
However, if one-dimensionality is achieved, local independence will also be fulfilled (there is no interdependence of items or shared variance that is not related to the measured dimension), so sometimes the two hypotheses are discussed together.
Muiz (2010) highlights the importance of advances in the field of psychometry and in the interpretation of tests, so the logical thing is that we are starting to take another step in that direction, since the tests analyzed under the IRT paradigm show at least disturbing results on how the measurement is currently performed.