Statistical analysis of student performance in redesigned developmental mathematics courses
- WCU Author/Contributor (non-WCU co-authors, if there are any, appear on document)
- Malgorzata J. Chockla (Creator)
- Institution
- Western Carolina University (WCU )
- Web Site: http://library.wcu.edu/
- Advisor
- John Wagaman
Abstract: Colleges and universities are focusing their efforts on improving the instruction in developmental
mathematics courses. In 2013, community colleges in North Carolina were in
the process of implementing the redesigned approach to teaching developmental mathematics
with the goal of improving student graduation rates. The purpose of this study
is to investigate the differences in academic improvements of developmental mathematics
students in order to evaluate the effectiveness of the redesigned MyMathLab (MML)
courses. This study investigates the following variables: College Placement Test (CPT)
scores in Algebra, Arithmetic, Reading Comprehension, and Sentence Structure, gender,
and instructional method. Multiple regression analyses were performed using the statistical
computing software, R. In Phase I of this study, two linear regression models were
developed to predict student academic improvement in MML and Educo developmental
mathematics courses using the standardized CPT scores, gender, and methodological indicator
as potential predictors. In Phase II, three linear models were analyzed to predict
student academic performance in redesigned MML classes. Using the data from Phase II,
three additional regression models were developed with the MML post-test as the response
variable and the CPT scores, gender, and the MML pre-test as the set of possible predictors
to identify “at-risk” students. An out-of-sample prediction method was used to evaluate the
misclassification rate in identifying “at-risk” students.
The results of this study suggest that Algebra and Arithmetic CPT scores are significant
predictors of student academic improvement. However, for each model, less than 50%
of the variability in student improvement is explained by the linear relationship between the
variables. Based on the results of this study, students enrolled in module 050 MML classes
at Southwestern Community College (SCC) showed greater improvement than Educo students.
Furthermore, the predictive models that include CPT scores and gender as the only
predictors of learning can be employed to identify “at-risk” students at the beginning of
each school semester. In the conclusion of the thesis, the limitations and implications of
this study are discussed.
Statistical analysis of student performance in redesigned developmental mathematics courses
PDF (Portable Document Format)
1858 KB
Created on 11/19/2013
Views: 10552
Additional Information
- Publication
- Thesis
- Language: English
- Date: 2013
- Keywords
- developmental education, multiple regression, redesigned mathematics courses
- Subjects
- Mathematics -- Remedial teaching -- North Carolina, Western -- Evaluation
- Mathematics -- Study and teaching (Higher) -- North Carolina, Western -- Evaluation
- Community college students -- North Carolina, Western -- Evaluation