Comprehensive Statistical Analysis of a Mathematics Placement Test PROCEEDINGS
Michael Pilant, Robert Hall, Eunju Jung, Texas A&M University, United States
Society for Information Technology & Teacher Education International Conference, in Austin, Texas, USA Publisher: AACE, Chesapeake, VA
As part of an NSF STEP grant, a math placement exam (MPE) has been developed at Texas A&M University for the purpose of evaluating the pre-calculus mathematical skills of entering students. It consists of 33 multiple-choice questions, and is taken online. A score of 22 or higher is required in order to register for Calculus I. To date, more than 15,000 students have taken the MPE. This paper focuses on the psychometric properties of the MPE based on analysis of test score results over a four-year period from 2008 to 2011. Item Response Theory (IRT), confirmatory factor analysis (CFA) and the computation of Cronbach's alpha have been performed. The value for Cronbach's alpha exceeds 0.90. This is comparable to high-stakes placement tests such as the SAT and the Advanced Placement tests. A brief analysis of the degree to which student performance in Calculus I can be predicted using MPE scores is also presented.
Pilant, M., Hall, R. & Jung, E. (2012). Comprehensive Statistical Analysis of a Mathematics Placement Test. In P. Resta (Ed.), Proceedings of Society for Information Technology & Teacher Education International Conference 2012 (pp. 4432-4439). Chesapeake, VA: AACE. Retrieved March 10, 2014 from http://www.editlib.org/p/40313.
© 2012 AACE