Item Response Theory: What It Is and What It Is Used For In Psychometry

Psychometrics is a discipline framed within experimental psychology, which aims to study and determine how psychological tests are constructed. Within it we find different models that have tried to facilitate this task (the construction of pots).

In this article we will talk about one of these models: element response theory. We tell you what it is, what limitations it has overcome compared to its previous model (classical testing theory), what it is used for and what are its basic concepts and characteristics.

    Psychology tests

    In the field of psychology, tests are procedures that allow us to collect large amounts of information (or very specific information) in relation to something that we want to discover or study about an individual or a group of. between them (for example a personality trait, anxiety, motivation, etc.).

    How are the pots constructed? They are developed from a series of psychometric models that allow us to assess the quality of the measurement of these tests., As well as obtain certain guarantees from this measure.

    In psychometry (which we will see later), there are different “Test Theories”, which form a frame of reference, both theoretical and methodological, to group together the different models and theories that will allow us to construct and use correctly the tests. Below, we’ll explore one of these models: Item Response Theory (IRT).

    Element Response Theory (IRT)

    Item Response Theory (IRT), also known as “Item Characteristic Curve Theory”, “Latent Trait Theory” (TRL) or “Reagent Response Theory” (TRR), is a theory that is psychometric. This theory it is used in the field of psychology to build different psychological tests and tests.

    For its part, psychometry is part of experimental psychology; it is a discipline, responsible for studying and developing all those methods and theories used to measure the psychological variables of people.

    Item Response Theory overcame the drawbacks or limitations of a previous theory: Classical Test Theory (TCT). This latter theory was developed by Charles Spearman in 1904; this is the theory with which psychometry began (the first), and sought to explain from a value in a test, obtained by a person, a true value can be extrapolated or concluded in relation to the manifestation of a characteristic or personality trait studied.

      What is the IRR for?

      The purpose of item response theory is to specify the relationship between the empirical scores obtained by a subject (or subjects) in a test, and an unobservable characteristic or trait studied in that subject (or subjects). An example of a trait to measure might be impulsivity, extraversion, introversion, etc.

      Thus, the theory of the response to the item is used to construct measurement (test) instruments with properties which do not vary between populations; This way, if two people have the same measured shooting level, both will have the same probability of giving the same answer, And this is independent of the population to which they belong.

      Overcome the limitations of TST

      As we saw at the beginning, item response theory overcomes some of the limitations presented by classical test theory.

      • The new theory is formulated at the overall test level, not at the item level.
      • Subject scores depend on the particular content of the test and its difficulty.
      • The difficulties are overcome with the parallelism of the measures.
      • The assumed homoscedasticity of measurement errors is overcome (IRR allows to obtain an error term for different skill levels)
      • Now the tests are also suitable for subjects who are not of average ability and from the majority population.

      Basic concepts and features

      In order to better understand the theory of the response to the element, we will see some of its basic concepts and most striking features:

      1. Observed score

      It should be clear that the score observed in a test is a random variable, with a certain distribution. This distribution depends on two variables: the subject’s level of aptitude or ability, and how the trait is assessed by the item. (Where are you).

      2. Dimensionality

      This concept is also part of item response theory. Dimensionality is part of the latent trait. Any individual can be described in a trait determining the values ​​of these dimensions; in practice, we speak of one-dimensional models.

      3. Local independence

      Another characteristic of item response theory is the local independence of the items and subjects examined. So when we talk about local independence, we mean that the probability p (x) that a subject answers correctly to an item is not influenced by the answers given to other items.

      On the other hand, if the unidimensionality mentioned in the previous point is respected, the local independence in the test is also respected.

      4. Test information function

      Another concept or idea that is part of element response theory is the test information function. This function is actually a property of the test, and it is what allows us to calculate how much information a test can give us at any skill level.

      Thus, the higher the informational function of a test provides for a given skill level, the more discrimination it will have for that level and the more measurement error will exist in the test.

      5. Characteristic curve of the article

      This curve, also called the regression curve, represents the expected values ​​in an element on the variable “fitness”.

      Parameters of the characteristic curve of the article

      In relation to this curve mentioned, specific to the Theory of response to the item, appear a series of associated parameters, the “parameters of the characteristic curve of the item”, which are three and which are represented by means of letters:

      1.B: object difficulty

      It consists of the subject’s aptitude level, which is located at the turning point of the curve. The greater the movement to the right, the greater the difficulty of the object (the harder it is).

      2.A: element discrimination

      The discrimination of the element is the slope of the curve; more pending, greater discrimination of the article.

      3. C: pseudo-luck or divination

      Finally, the parameter C is pseudoazar or divination; it consists of the probability of hitting an element at random and is measured in the lower asymptote of the curve. For the element to be appropriate, this parameter must be at most equal to 0.35.

      Bibliographical references:

      • Attorresi, HF, Lozzia, GS, Abal, JP, Galibert, MS and Aguerri, ME (2009). Theory of the response to the elements. Basic concepts and applications for the measurement of psychological constructs. Argentine Journal of the Psychological Clinic, 18 (2): 179-188.
      • Martinez, R. (1995). Psychometry: Theory of psychological and educational tests. Madrid: Synthesis.
      • Muñiz, J. (1997). Introduction to item response theory. Madrid: Pyramid Editions.
      • Santisteban, C. (1990). Psychometrics: theory and practice in test construction. Madrid: Ediciones Norma.

      Leave a Comment