Details

Modeling Distributions of Test Scores with Mixtures of Beta Distributions Modeling Distributions of Test Scores with Mixtures of Beta Distributions

by Feng, Jingyu 1973-

Abstract (Summary)
Test score distributions are used to make important instructional decisions about students. The test scores usually do not follow a normal distribution. In some cases, the scores appear to follow a bimodal distribution that can be modeled with a mixture of beta distributions. This bimodality may be due different levels of students’ ability. The purpose of this study was to develop and apply statistical techniques for fitting beta mixtures and detecting bimodality in test score distributions.

Maximum likelihood and Bayesian methods were used to estimate the five parameters of the beta mixture distribution for scores in four quizzes in a cell biology class at Brigham Young University. The mixing proportion was examined to draw conclusions about bimodality. We were successful in fitting the beta mixture to the data, but the methods were only partially successful in detecting bimodality.

Bibliographical Information:

Advisor:

School:Brigham Young University

School Location:USA - Utah

Source Type:Master's Thesis

Keywords:mixture distribution beta bayesian likelihood

ISBN:

Date of Publication:07/08/2005

© 2009 OpenThesis.org. All Rights Reserved.