ri2 makes conducting randomization inference easy and (with the blessing of the original authors) is the successor package to ri.
ri2 has specific support for the following:
Additionally, ri2 provides:
You can install ri2 is on CRAN
If you’d like to install the most current development release, you can use the following code:
Here is the basic syntax for a two-arm trial:
library(ri2) #> Loading required package: randomizr #> Loading required package: estimatr N <- 100 declaration <- declare_ra(N = N, m = 50) Z <- conduct_ra(declaration) X <- rnorm(N) Y <- .9 * X + .2 * Z + rnorm(N) dat <- data.frame(Y, X, Z) ri_out <- conduct_ri( formula = Y ~ Z, declaration = declaration, assignment = "Z", sharp_hypothesis = 0, data = dat ) plot(ri_out)
summary(ri_out) #> coefficient estimate two_tailed_p_value null_ci_lower null_ci_upper #> 1 Z -0.5887379 0.022 -0.4911486 0.4927481
The development of ri2 is supported by a Standards Grant from EGAP and the UK Department for International Development.