2026 ASEE Annual Conference & Exposition

Developing students' systematic and analytical thinking remains an essential but challenging goal in engineering education. These cognitive skills are critical for solving complex engineering problems that involve uncertainty, interdependence, and large amounts of data, yet they are often taught in isolation through disconnected tools or examples. Bayesian systems modeling offers a powerful framework for integrating key industrial engineering concepts such as uncertainty quantification, interdependence modeling, and data-driven decision-making. This paper introduces a project-based learning module implemented in a senior capstone course to help students develop systematic thinking through the application of Bayesian multivariate spatial modeling. This model provides students with an applied experience that draws on multiple analytical skills within a realistic case study.
In the proposed module, students investigate how mobile phone, internet, and computer access are jointly distributed across multiple districts using Bayesian methods that explicitly account for spatial correlation and uncertainty. The project guides students through exploratory data analysis, regression modeling, spatial correlation analysis, Bayesian inference, and interpretation of posterior estimates and their credible intervals.
The module explicitly targets two ABET- aligned competencies from the Industrial Engineering Mapping Matrix: 1) Formulate & Solve Complex Engineering Problems and 2) Develop/Conduct Experiments - Analyze/Interpret Data - Form Conclusions. Students can apply principles of engineering, science and mathematics by implementing Bayesian systems modeling to reinforce both quantitative skills and systems-level thinking in a globally relevant socio-technical context. The paper outlines the course context and learning objectives to support student engagement with this case-based module. It also discusses the implementation plan, including project structure, student deliverables, and assessment strategies. By embedding Bayesian modeling into applied problem-solving and data-driven projects, this work contributes a transferable instructional approach to integrating probabilistic reasoning into systems-level decision-making engineering education, by teaching students’ systematic and analytical thinking in complex socio-technical contexts.