Statistical Analysis to Support Improved Student Outcomes

• Activity Number: 391 - Improving Quality
• Type: Contributed
• Date/Time: Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
• Sponsor: Quality and Productivity Section
• Author(s): Joanne Wendelberger* and Amy L. Wiseman and Claire McKay Bowen and Benjamin H. Sims and Celeste Alexander and Pedro Reyes
• Companies: Los Alamos National Laboratory and Texas State University and Urban Institute and Los Alamos National Laboratory and University of Texas at Austin and University of Texas at Austin
• Keywords: education; data analytics; statistical modeling; quality improvement

Abstract

A supply of individuals trained in STEM is needed to meet the employment needs of the United States. To address this need, an analytics initiative was executed to analyze multiple data streams relevant to education and learning. The goal of this effort was to identify factors that impact educational outcomes. Knowledge about these factors can potentially be used to improve the educational environment. This project makes use of big data and analytics to build predictive models for improving student success. Data is used to help understand how children, adolescents, and adults progress throughout the education pipeline. While additional study and verification of the factors identified by the models is recommended, knowledge of factors affecting students with different attributes could be a powerful source of information for addressing the needs of students and helping them to achieve successful outcomes such as on-time high school graduation, higher education degree completion, and STEM degree completion. Putting knowledge about different effects into action can pave the way for increasing the number of individuals who complete high school, college, and STEM degrees.