Investigating Generative Factors of Score Matrices (2007)

by Titus Winters, Christian R. Shelton, and Tom Payne

Abstract: An implicit assumption in psychometrics and educational statistics is that the generative model for student scores on test questions is governed by the topcis of those questions and each student's aptitude in those topics. That is, a function to generate the matrix of scores for m students on n questions should reply on each student's ability in a set of t topics, and the relevance of each question to those topics. In this paper, we investigate score matrices from univeristy-level computer science courses, and demonstrate that no such structure can be extracted from this data. Utilizing unsupervised machine learning techniques we provide evidence calling into question this fundamental assumption of educational statistics.

Download Information

Titus Winters, Christian R. Shelton, and Tom Payne (2007). "Investigating Generative Factors of Score Matrices." Thirteenth International Conference on Artificial Intelligence in Education (pp. 479-486). pdf        

Bibtex citation

@inproceedings{WinShePay07,
   author = "Titus Winters and Christian R. Shelton and Tom Payne",
   title = "Investigating Generative Factors of Score Matrices",
   booktitle = "Thirteenth International Conference on Artificial Intelligence in Education",
   booktitleabbr = "{AIED}-2007",
   year = 2007,
   pages = "479--486",
}

full list