Learning decomposition: fit exponential learning curves to compare the relative effectiveness of types of pedagogical support¶

Strategy · All strategies
Evidence · no claims cited

Description¶

Learning decomposition is a method for studying pedagogical support in which, per the review, "Learning decomposition fits exponential learning curves to performance data, relating a student's later success to the amount of each type of pedagogical support the student received up to that point". The relative weights in the best-fit model infer each support type's relative effectiveness for promoting learning. The review presents it as a popular method for discovering which support types work best overall or for different student groups.

Design Implications¶

Context¶

Requirements¶

• Performance data capturing students' later success and the amounts of each type of pedagogical support received

Constraints¶

Target Learners¶

• students using interactive learning software

Target Learning Goals¶

• identifying which practice or support types most promote learning

Related Strategies¶

• Fit change-score versus pretest-score data with α and γ process models to diagnose learning processes and distinguish student ability from instruction impact

Examples¶

-

Key Sources¶

• Ryan S.J.D. Baker and Kalina Yacef. (2009). The State of Educational Data Mining in 2009: A Review and Future Visions. Journal of Educational Data Mining, Article 1, Vol 1, No 1, Fall 2009. https://jedm.educationaldatamining.org/index.php/JEDM/article/view/8