Doctor of Philosophy (PhD)
Educational Theory, Policy, and Practice
College student retention rates are often used as a measure of institutional accountability, institutional success, and are used more frequently as a means of determining resource allocation. Understanding what factors impact the retention of college students has become critical to institutions of higher education. The study of the factors that impact student retention has been plagued with methodological concerns, especially the longitudinal and hierarchical nature of retention data. The purpose of this study was to investigate college student retention using a multilevel discrete-time hazard model. A multilevel discrete-time hazard model deals with many of the concerns associated with analyzing college student retention data, such as censored observations, the multilevel nature of the data, and variables that change over time. Gender, ethnicity and school-type were used to model the timing of students leaving a university from a cohort of first-time freshmen over five year period.
Document Availability at the Time of Submission
Release the entire work immediately for access worldwide.
Guillory, Christopher W., "A multilevel discrete - time hazard model of retention data in higher education" (2008). LSU Doctoral Dissertations. 3101.