Reproduce “Dynamic Bayesian Item Response Model with Decomposition (D-BIRD): Modeling Cohort and Individual Learning Over Time” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hansol Lee, Jason B. Cho, David S. Matteson, Benjamin W. Domingue
D-BIRD estimates students’ ability trajectories from sparse binary Rasch responses by combining a shared cohort trend with individual deviations. In 250 simulations, it achieved mean squared error of 0.216 and empirical coverage of 0.960, compared with 0.260 and 0.901 for Hetero-RW. These results are limited to simulations generated with both components; platform slopes are descriptive estimates, not causal effects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.