@peng_ding
⚠️ Unofficial community showcase of software for the design-based & randomization-inference methods associated with Prof. Peng Ding (his EValue, plus the canonical packages implementing these methods). Not affiliated — all credit to each package's authors.
Workflows
Random assignment by design (randomizr)
Reproducible random assignment — simple, complete, block, cluster, stratified — with the exact assignment probabilities design-based inference needs.
Randomization inference, packaged (ri2)
Exact Fisher randomization tests and sharp-null confidence intervals for any randomization scheme — the packaged version of the design-based test.
Design-based estimators done fast (estimatr)
Lin's covariate-adjusted estimator and Neyman/HC2 robust standard errors for randomized experiments — one fast function, design-based inference.
Sensitivity analysis & the E-value (Ding & VanderWeele)
Reports how strong an unmeasured confounder would have to be, on the risk-ratio scale, to fully explain away an observed association.