Item response theory analysis of the mechanics baseline test
Name
pritch item response.pdf
Size
188.5 KB
Format
Adobe PDF
Checksum (MD5)
d45cd770ca31576937ffbcb157020464
Author(s)
Cardamone, Carolin
Abbott, Jonathan E.
Rayyan, Saif
Seaton, Daniel
Pawl, Andrew
Pritchard, David E.
Date Issued
August 2011
Journal
Proceedings of the Physics Education Research Conference, 2011
Publisher
American Institute of Physics
Citation
Cardamone, Caroline N. et al. “Item Response Theory Analysis of the Mechanics Baseline Test.” 2011 Physics Education Research Conference : Omaha, Nebraska, USA : 3-4 August 2011" editors, N. Sanjay Rebello, Paula V. Engelhardt, Chandralekha Singh., American Institute of Physics, Melville, N.Y.2012. (AIP Conf. Proc. p. 135–138). CrossRef. Web.
Version
Author's final manuscript
Abstract
Item response theory is useful in both the development and evaluation of assessments and in computing standardized measures of student performance. In item response theory, individual parameters (difficulty, discrimination) for each item or question are fit by item response models. These parameters provide a means for evaluating a test and offer a better measure of student skill than a raw test score, because each skill calculation considers not only the number of questions answered correctly, but the individual properties of all questions answered. Here, we present the results from an analysis of the Mechanics Baseline Test given at MIT during 2005-2010. Using the item parameters, we identify questions on the Mechanics Baseline Test that are not effective in discriminating between MIT students of different abilities. We show that a limited subset of the highest quality questions on the Mechanics Baseline Test returns accurate measures of student skill. We compare student skills as determined by item response theory to the more traditional measurement of the raw score and show that a comparable measure of learning gain can be computed.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Massachusetts Institute of Technology. Department of Physics
Massachusetts Institute of Technology. Office of Digital Learning
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1063/1.3680012
