Resources for Item Response Theory (June 28, 2006). Category: Statistical computing

One area that I would like to investigate when I have time is Item Response Theory (IRT). This is an approach that is sometimes called a latent trait model or a Rasch model, though there are some technical distinctions between these terms.

IRT is popular in testing as it allows for the modeling of the difficulty of individual questions on a test and their ability to discriminate among individuals of different abilities. It can also be used for examining the validity of a scale that consists of the sum of a number of Likert scale items (or in general a sum of ordinal scale items).

There is a free library in R to perform these calculations,

• cran.r-project.org/src/contrib/Descriptions/ltm.html

and some very nice web resources describing IRT at

• edres.org/irt/
• luna.cas.usf.edu/~mbrannic/files/pmet/irt.htm
• work.psych.uiuc.edu/irt/tutorial.asp
• appliedresearch.cancer.gov/areas/cognitive/item.html

 An interesting application of IRT appears at

• Using item response theory to explore the psychometric properties of extended matching questions examination in undergraduate medical education. B. Bhakta, A. Tennant, M. Horton, G. Lawton, D. Andrich. BMC Med Educ 2005: 5(1); 9. [Medline] [Abstract] [Full text] [PDF] (Model, Item Response Theory)

This webpage was written by Steve Simon and was last modified on 07/08/2008.