Causal Inference Networks: Unraveling the Complex Relationships Between Curriculum Complexity, Student Characteristics, and Performance in Higher Education
- Conference
- Location
-
Portland, Oregon
- Publication Date
-
June 23, 2024
- Start Date
-
June 23, 2024
- End Date
-
June 26, 2024
- Conference Session
- Tagged Topics
-
Diversity and Data Science & Analytics Constituent Committee (DSA)
- Page Count
-
24
- DOI
-
10.18260/1-2--48449
- Permanent URL
-
https://peer.asee.org/48449
- Download Count
-
297
Paper Authors
Ahmad Slim The University of Arizona
Dr. Ahmad Slim is a PostDoc researcher at the University of Arizona, where he specializes in educational data mining and machine learning. With a Ph.D. in Computer Engineering from the University of New Mexico, he leads initiatives to develop analytics solutions that support strategic decision-making in academic and administrative domains. His work includes the creation of predictive models and data visualization tools that aim to improve student recruitment, retention, and success metrics. Dr. Slim's scholarly contributions include numerous articles on the application of data science in enhancing educational practices.
Gregory L. Heileman
The University of Arizona
orcid.org/0000-0002-5221-5682
Gregory (Greg) L. Heileman currently serves as the Associate Vice Provost for Academic Administration and Professor of Electrical and Computer Engineering at the University of Arizona, where he is responsible for facilitating collaboration across campus t
Melika Akbarsharifi The University of Arizona
Melika Akbarsharifi is a Master's student in Electrical and Computer Engineering at the University of Arizona, studying under Professor Gregory L. Heileman. Her research at the Curricular Analytics Lab focuses on using machine learning and data analysis to enhance educational outcomes. Key contributions include developing a cohort-tracking analytics platform that assists in improving graduation rates by addressing curricular barriers.
Melika has co-authored papers presented at conferences such as the ASEE Annual Conference and Exposition, exploring the intersection of curriculum complexity and student performance. Her technical proficiency spans multiple programming languages and cloud computing, furthering her research into innovative educational technologies.
Kristina A Manasil The University of Arizona
Kristi Manasil is a first-year PhD student in the School of Information at the University of Arizona. She received her bachelor's degree in Computer Science from the University of Arizona. She is interested in data visualization, machine learning, human computer interaction, learning analytics and educational data mining.
Ameer Slim University of New Mexico
Abstract
Numerous research studies have explored the influence of curriculum complexity on student performance, primarily focusing on factors like retention and graduation rates. Many of these investigations have employed conventional machine learning and data analysis methods, often yielding results that are challenging to interpret and convey effectively. Furthermore, these studies have generally lacked a comprehensive framework for elucidating how variables such as student gender and prior academic preparation contribute to the selection of specific university programs, each characterized by its own structural complexity. In essence, these studies have not presented foundational models to elucidate the fundamental mechanisms underlying the causal relationship between the complexity of university programs, student attributes, and success metrics.
In our present study, we introduce an innovative causal inference network model that conceptualizes the university as a dynamic system with interrelated causal relationships among its various components, encompassing students, faculty, programs, colleges, graduation rates, and more, each with their respective dependencies. This model affords us the ability to comprehend and visually represent the direction of causality between different variables, enabling us to investigate how changes in one variable, the causal factor, impact another variable. This implementation of causality not only facilitates predictive tasks, like other conventional machine learning models (i.e., hypothetical causation), but also enables us to conduct objective ``what-if" analyses (i.e., counterfactual causation) within the research context.
In this study, we leverage real-world student data from 30 different universities across the United States. The richness and diversity of our dataset empower us to draw robust insights into the causal relationships among various factors that influence student performance, particularly the complexity of the curriculum. One noteworthy preliminary finding from our application of this causal model is that students of certain genders, academic backgrounds, or socioeconomic conditions tend to gravitate toward university programs characterized by specific structural complexities. The breadth and scale of our dataset contribute significantly to our ability to derive substantive and compelling conclusions from our research endeavors.
Slim, A., & Heileman, G. L., & Akbarsharifi, M., & Manasil, K. A., & Slim, A. (2024, June), Causal Inference Networks: Unraveling the Complex Relationships Between Curriculum Complexity, Student Characteristics, and Performance in Higher Education Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. 10.18260/1-2--48449
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2024 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015