Abstract and Keywords
Item response theory (IRT) comprises a collection of mathematical and statistical models and methods that are used in the assembly and scoring of psychological questionnaires and scales. IRT is used to investigate the statistical properties of categorical responses to questions, or other observations that may be indicators on a test or scale. IRT models are used for item analysis and scoring for items with dichotomous or polytomous responses. Statistical analysis using IRT summarizes the degree of endorsement or severity of each response, the strength of the relation between the item response and the underlying construct, and the degree to which a collection of questions or other indicators measure one coherent construct, or more than one. IRT is also used to investigate the degree to which item responses exhibit differential item functioning, or a lack of desired invariance, over groups. Finally, IRT is used to compute scale scores that are comparable across alternate forms of a questionnaire, and that may have better statistical properties than more traditional summed scores. This chapter illustrates these ideas with empirical examples.
Access to the complete content on Oxford Handbooks Online requires a subscription or purchase. Public users are able to search the site and view the abstracts and keywords for each book and chapter without a subscription.
If you have purchased a print title that contains an access token, please see the token for information about how to register your code.