Data and Code for "Cluster trials inference with CARE"

This repository contains the data and replication files for the paper “Cluster Trials Inference with CARE” by Sergey Alexeev and Rachael L. Morton. The materials reproduce all analyses and simulations in the manuscript. The repository includes: Processed datasets used in the empirical examples and simulations. Simulation scripts implementing the treatment reassignment and cluster imbalance scenarios described in the paper. Keywords: cluster-robust inference, cluster-randomised clinical trials, model robustness, jackknife variance estimator, assumption sensitivity, pragmatic design The replication package demonstrates that CRTs—especially pragmatic designs—often exhibit substantial heterogeneity in cluster sizes and structures, which can distort inference. The CARE protocol provides a simple, scalable framework for robust analysis that integrates these considerations into standard trial Statistical Analysis Plans.