Selected Research Papers

Selected Journal Articles and Publications

  • “The value of common definitions in student success research: Setting the stage for adoption and scale.” Vignare, Karen., Wagner, Ellen., & Swan, Karen. (2017). Journal of Internet Learning, April / May 2017.
  • “Scaling student success with predictive analytics: Reflections after four years in the data trenches.” Wagner, Ellen & Longanecker, David. (2016). Change: The Magazine of Higher Learning, 48:1, 52-59, DOI: 10.1080/00091383.2016.11210
  • “Retention, Progression, and the Taking of Online Courses.” James, S., Swan, K., & Daston, C. (2015). Online Learning, Volume 20 Number 2 (22 December 2015). Click here to read the article.
  • “Predictive models based on behavioral patterns in higher education.” Wagner, Ellen & Yaskin, David. (2015). Computing Research Association Data-Intensive Research in Education: Current Work and Next Steps. Report on Two National Science Foundation Sponsored Computing Research Education Workshops. Click here to read the article.
  • “Case Study: The Predictive Analytics Reporting (PAR) Framework and WCET.”  Wagner, Ellen & Davis, Beth, (2013). EDUCAUSE Review, Nov/Dec 2013. Click here to read the article.
  • “Data Changes Everything: Delivering on the Promise of Learning Analytics in Higher Education.” Wagner, Ellen & Ice, Phil (2012).  EDUCAUSE Review, July 2012. Click here to read the article.
  • “The PAR Framework Proof of Concept: Initial Findings from a Multi-Institutional Analysis of Federated Postsecondary Data.” Ice, Phil; Diaz, Sebastian; Swan, Karen; Burgess, Melissa; Sharkey, Mike; Sherrill, Jonathan; Huston, Dan; Okimoto, Hae (2012). Journal of Asynchronous Learning Networks, v16 n3 p63-86 Jun 2012. Click here to read the article

SSMx

The Student Success Matrix (SSMx) is a powerful tool to help many different stakeholders coordinate reflection and documentation of existing interventions and where they occur in the student lifecycle. A completed SSMx can connect various student risk types with supports that appropriately and effectively address the specific behavioral risk issues at the point the supports will be most likely to have the greatest positive effect. Our members work through the SSMx using an online tool, but we are providing the structure and essential definitions here and on the Data Cookbook, licensed under Creative Commons, to aid the wider higher education community.

Data Model

Common data definitions are critical to ensure that comparisons and aggregations are valid, reliable and repeatable. The PAR Framework developed core variables used as building blocks in various strategic combinations to craft meaningful outcome measures and actionable predictors of student risk which further highlights the importance of common definitions. Our members have a dedicated team of specialists and data scientists to help extract, process, and analyze institutional data – and build benchmarks against other member institutions – but we are providing the essential definitions here and on the Data Cookbook, licensed under Creative Commons, to aid the wider higher education community.