Incorporate teacher-observed data on behaviors, attitudes, and aspirations into predictive models¶

Strategy · All strategies
Evidence · 1 claim (1 for) · 1 study (1 theoretical), q1 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

The article points to teachers as a source of information that statistical models usually miss, calling them "a veritable treasure trove of data on student behaviors, attitudes, and aspirations." The strategy is to draw this teacher-held information into analytics so models reflect what educators already know. The article presents it as a way to avoid the pitfalls of industry-style modeling in schools.

Design Implications¶

Context¶

Requirements¶

• Access to teachers' knowledge of individual students' behaviors, attitudes, and aspirations

Constraints¶

• This information is currently not typically included in a statistical model, per the article

Target Learners¶

• K-12 students

Target Learning Goals¶

• Improving the accuracy and fairness of student risk prediction

Claims¶

• Teachers know far more about their students than an investor knows about a stock, including data not typically in statistical models [+W]

Related Strategies¶

Examples¶

-

Key Sources¶

• James Soland. (2015). Is Moneyball the next big thing in education? Phi Delta Kappan 96(4), 64–67. https://www.nwea.org/research/publication/is-moneyball-the-next-big-thing-in-education/