Major Changes and Attrition: An Information Theoretic and Statistical Examination of Cohort Features Stratified on Major Switches

George D. Ricco; James F. Ryan

Download Paper | Permalink

Conference: 2015 ASEE Annual Conference & Exposition
Location: Seattle, Washington
Publication Date: June 14, 2015
Start Date: June 14, 2015
End Date: June 17, 2015
ISBN: 978-0-692-50180-1
ISSN: 2153-5965
Conference Session: Persistence and Retention
Tagged Division: Educational Research and Methods
Page Count: 10
Page Numbers: 26.1103.1 - 26.1103.10
DOI: 10.18260/p.24440
Permanent URL: https://peer.asee.org/24440
Download Count: 473

Paper Authors

biography

George D. Ricco Purdue University, West Lafayette

visit author page

George D. Ricco is the KEEN Program Coordinator at Gonzaga University in the School of Engineering and Applied Science. He completed his doctorate in engineering education from Purdue University’s School of Engineering Education. Previously, he received a M.S. in earth and planetary sciences studying geospatial imaging and a M.S. in physics studying high-pressure, high-temperature FT-IR spectroscopy in heavy water, both from the University of California, Santa Cruz. He holds a B.S.E. in engineering physics with a concentration in electrical engineering from Case Western Reserve University. His academic interests include longitudinal analysis, visualization, semantics, team formation, gender issues, existential phenomenology, and lagomorph physiology. He lives in romantic Spokane with his leporidae partner, Rochelle Huffington Nibblesworth.

visit author page

biography

James F. Ryan III Rensselaer Polytechnic Institute

visit author page

Mr. James F. Ryan is a Ph. D. student at Rensselaer Polytechnic Institute in the Department of Mathematics. He attained a B.S. in both Mathematics and Mathematical Statistics from Purdue University and attained an M.S. in Mathematics with a focus on Mathematical Data Mining fro Tarleton State University. James' current research interests are in data analytics and mathematical techniques for data discovery and mining in myriad spaces. He has worked on case studies ranging from time series analysis of satellite data, risk analysis across shipping lanes and prescriptive analytics in the healthcare field.

visit author page

Download Paper | Permalink

Abstract

Major Changes and Attrition: An Information Theoretic and Statistical Examination of Cohort Features Stratified on Major Switches Previous work in education statistics on major switching has demonstrated that studentswho eventually graduate take longer to leave the system with every change of major. The sametrend, unexpectedly, was also discovered for students who inevitably fail to graduate. A betterunderstanding of how these trends can be differentiated as the number of major switches increasewould be a great boon to policymakers on both institutional and departmental levels of decisionmaking. We utilize the Multiple-Institution Database for Investigating Engineering LongitudinalDevelopment (MIDFIELD) as a base set to compute relevant statistical and information theoreticvalues for the cohorts of students who eventually graduate the system and those that do not,breaking each subset up by the number of majors an observation is shown to have. The use of theMIDFIELD database for statistical modeling and high level feature analysis has been previouslydocumented and its coverage of over 13% of US engineering students makes it ideal for this task. The cohorts above are created from observations of 871,742 first-time in college (FTIC)students across eleven US institutions. We examine these broken up cohorts by looking atdemographic and temporal features, in particular the terms until attrition, and perform odds ratiotests to examine the probability of a student, having switched a certain number of majors,belonging to a particular cohort. We also compute information theoretic values such as mutualinformation to develop a proxy for how much we can know about these particular classes ofstudents given information on their major switches. The values above will be presented with similar work done on the database itself toprovide a high level examination of the feature space present in MIDFIELD and how it comparesto those students graduating or not. The results here couple with concurrent work to derive moreeffective classification and statistical modeling of the phenomena of major switches at a moregranular level.

Citation
Format

Ricco, G. D., & Ryan, J. F. (2015, June), Major Changes and Attrition: An Information Theoretic and Statistical Examination of Cohort Features Stratified on Major Switches Paper presented at 2015 ASEE Annual Conference & Exposition, Seattle, Washington. 10.18260/p.24440

TY  - CPAPER
AB  -     Major Changes and Attrition: An Information Theoretic and Statistical Examination of Cohort                               Features Stratified on Major Switches        Previous work in education statistics on major switching has demonstrated that studentswho eventually graduate take longer to leave the system with every change of major. The sametrend, unexpectedly, was also discovered for students who inevitably fail to graduate. A betterunderstanding of how these trends can be differentiated as the number of major switches increasewould be a great boon to policymakers on both institutional and departmental levels of decisionmaking.        We utilize the Multiple-Institution Database for Investigating Engineering LongitudinalDevelopment (MIDFIELD) as a base set to compute relevant statistical and information theoreticvalues for the cohorts of students who eventually graduate the system and those that do not,breaking each subset up by the number of majors an observation is shown to have. The use of theMIDFIELD database for statistical modeling and high level feature analysis has been previouslydocumented and its coverage of over 13% of US engineering students makes it ideal for this task.         The cohorts above are created from observations of 871,742 first-time in college (FTIC)students across eleven US institutions. We examine these broken up cohorts by looking atdemographic and temporal features, in particular the terms until attrition, and perform odds ratiotests to examine the probability of a student, having switched a certain number of majors,belonging to a particular cohort. We also compute information theoretic values such as mutualinformation to develop a proxy for how much we can know about these particular classes ofstudents given information on their major switches.        The values above will be presented with similar work done on the database itself toprovide a high level examination of the feature space present in MIDFIELD and how it comparesto those students graduating or not. The results here couple with concurrent work to derive moreeffective classification and statistical modeling of the phenomena of major switches at a moregranular level. 
AU  - George D. Ricco
AU  - James F. Ryan III
CY  - Seattle, Washington
DA  - 2015/06/14
PB  - ASEE Conferences
TI  - Major Changes and Attrition: An Information Theoretic and Statistical Examination of Cohort Features Stratified on Major Switches 
UR  - https://peer.asee.org/24440
DO  - 10.18260/p.24440
ER  -