Do developmental mathematics programs have a causal impact on student retention? An application of discrete-time survival and regression-discontinuity analysis |
| |
| Authors: | Sally A Lesik |
| |
| Institution: | (1) Department of Mathematical Sciences, Central Connecticut State University, New Britain, USA;(2) Department of Mathematical Sciences, Central Connecticut State University, 1615 Stanley Street, New Britain, CT 06050, USA |
| |
| Abstract: | The impact of academic programs—such as developmental mathematics programs—on student retention, has been a controversial
topic for administrators, policy makers, and faculty in higher education. Despite deep interest in the effectiveness of these
programs in retaining students, scholars have been unable to determine whether such programs have a causal impact on student
retention. Rather than assigning students to a developmental program based on a random assignment process as in a true experiment,
most of the existing research up to this point has been non-experimental and has focused exclusively on whether student background
and demographic characteristics are statistically significant predictors of dropout. Furthermore, prior research is also limited
by its reliance on cross-sectional, retrospective designs despite the longitudinal nature of the dropout phenomenon. In this
paper, I report the results of a unique piece of research which embeds a regression-discontinuity design within the framework
provided by discrete-time survival analysis. By combining these two approaches, I was able to obtain an unbiased estimate
of the causal impact of participating in a developmental program in mathematics, and confirm that the risk of leaving college
among students who participate in developmental mathematics programs was significantly lower than for equivalent students
who did not participate in such programs. |
| |
| Keywords: | student retention developmental mathematics regression-discontinuity design discrete-time survival analysis |
| 本文献已被 SpringerLink 等数据库收录！ |
|
