1. Home
  2. Publications
  3. Two-Step Imputation Combining IRT and Deep-Learning Methods for Large-Scale Survey Assessments

Two-Step Imputation Combining IRT and Deep-Learning Methods for Large-Scale Survey Assessments

van Rijn, Peter Ali, Usama Dwivedi, Priyadarshini
(2026)
Download PDF8.7 MB
Large-scale assessments (LSAs) rely on matrix-sampling designs that generate substantial planned missing item-response data. In this study, we report on a two-step imputation method that combines item response theory (IRT) and deep learning techniques to generate a complete item-response matrix for reporting, such as the market-basket approach.