P1-28: Introducing Individualized Pathways and Resources to Adaptive Control Theory-Inspired Scientific Education (iPRACTISE) System


By Jungmin Lee, Jonathan Park, Sy-Miin Chow, and Dennis Pearl, The Pennsylvania State University


Information

Educating statistical etiquettes— such as in data wrangling, reporting, and visualization –is crucial in this digital age. A hurdle to building nomothetic standards for teaching these practices is the large degree of heterogeneity in students’ backgrounds. This poster describes the development, testing, and implementation of a system, Individualized Pathways and Resources to Adaptive Control Theory-Inspired Scientific Education (iPRACTISE), by an interdisciplinary team at Penn State. iPRACTISE serves to enhance current data science training by using modern technology to personalize educational contents as guided by user input and automated control theory algorithms. With R programming as an example, we present a preliminary prototype of iPRACTISE, its foundational concepts, and examples of personalized training and assessment modules constructed via crowdsourced teaching content, assessment questions, student performance data, and control theory principles. The collaborative work of the iPRACTISE team is designed to help students diagnose deficiencies and connect to tailored training resources.


Poster Session - P1-28 - Introducing Individualized Pathways and Resources to Adaptive Control Theory-Inspired Scientific Education (iPRACTISE) System.pdf

register