If you have any problems related to the accessibility of any content (or if you want to request that a specific publication be accessible), please contact (firstname.lastname@example.org). We will work to respond to each request in as timely a manner as possible.
The Hazard of Graduation: Analysis of Three Multivariate Statistics Used To Study Multi-institutional Attendance
AuthorMuehlberg, Jessica Marie
AdvisorMiltenberger, Patricia K.
AltmetricsView Usage Statistics
Adelman (2006) observed that a large quantity of research on retention is "institution-specific or use institutional characteristics as independent variables" (p. 81). However, he observed that over 60% of the students he studied attended multiple institutions making the calculation of institutional effects highly problematic. He argued that the student, and not the institution, should be the unit of analysis when studying the societal impacts of postsecondary education. Ranco (1996) predicted that our current measures of success (4-year and 6-year graduation rates), as well as persistence rates (the measure of the number of students returning year-to-year) were soon to become outdated. All of these measures are dependent on a student remaining continuously enrolled at one single institution. Whatever the term used, current methods of measuring student success may become inadequate to explain the realities of college student attendance and persistence. College attendance patterns are no longer adequately represented using a linear model (Sturtz, 2006). Statistics capable of using multi-institutional attendance data need to be explored to determine which are not only capable of evaluating these complex data sets, but which are simple to understand and use so that policy makers and administrators may take ready advantage of them. This study reviews the common methodologies for studying student enrollment patterns and examines novel methodologies that may improve the analysis of multi-institutional attendance. This also study explored how a thorough understanding of several statistics (logistic regression, discriminant analysis, and survival analysis) can be applied to the study of multi-institutional attendance and how researchers and administrators can best select which tool should be used to understand the impacts of student completion.