home - login - register

PERC 2009 Abstract Detail Page

Previous Page  |  New Search  |  Browse All

Abstract Title: Using Cluster Analysis to Group Student Responses on the FMCE
Abstract: Previous work with applying cluster analysis to free response questions about two-dimensional motion has shown suggestive similarities between the groups found by the cluster analysis and the traditional classifications of student responses [1].   A comparison of cluster analysis and traditional classifications over a single class, however, was unable to make any hard and fast conclusions because the cluster analysis results were unreliable for that population size (N = 106) [2].  In this poster we present the results of making the same kind of pivot table comparison over a larger data set (N = 677) which served to reduce the amount of noise in the cluster analysis results.

[1] R. P. Springuel, M. C. Wittmann, and J. R. Thompson, Applying clustering to statistical analysis of student reasoning about two-dimensional kinematics, Physical Review Special Topics - Physics Education Research 3, 020107 (2007).
[2] R. P. Springuel, M. C. Wittmann, and J. R. Thompson, Comparing cluster analysis and traditional analysis methods in PER, AAPT Summer National Meeting (2007).
Abstract Type: Contributed Poster

Author/Organizer Information

Primary Contact: R. Padraic Springuel
University of Maine
5709 Bennett Hall
University of Maine
Orono, ME 04469
Phone: 207-581-1038
and Co-Presenter(s)
Name: Michael C. Wittmann
Institution: University of Maine