Test and Item Analysis via Shiny
-
Updated
Jun 8, 2026 - R
Test and Item Analysis via Shiny
DIF and DDF Detection by Non-Linear Regression Models.
Code and frozen results for "Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?" (NeurIPS 2026 TAE Workshop)
Product of Indicators (PI) for MIMIC Models in DIF detection
This package provides a function to detect differential item functioning in a rasch poisson count model.
A reliability and DIF report card for LLM-judge and human-rater scoring instruments.
R code for reproducing the simulations and PIAAC illustration in "Identifying Item Bias Without Conditioning: A Difference-in-Differences Approach".
Which AI model to use, and did the new version get worse, answered with statistical confidence at a tenth of the evaluation calls: item response theory for LLM benchmarks.
An adaptive testing engine: item response theory, maximum-information item selection, live ability estimation, and differential item functioning.
To associate your repository with the differential-item-functioning topic, visit your repo's landing page and select "manage topics."