Optimal Rerandomization Experimental Designs
Implements the complete randomization design (CRD) AKA Bernoulli Trial
Implements the balanced complete randomization design (BCRD)
Returns the objective value given a design vector as well an an object...
Naive Frobenius Norm Squared
Debiased Frobenius Norm Squared Var-Cov matrix
Debiased Frobenius Norm Squared Constant Times Var-Cov matrix
Generate Base Assignments and Sorts
Find the Optimal Rerandomization Design Exactly
Find the Optimal Rerandomization Design Under the Gaussian Approximati...
Find the Optimal Rerandomization Design Under the Tail and Kurtosis Ap...
Optimal Rerandomization Threshold Search for Experimental Design
Plots a summary of a optimal_rerandomization_obj object
Plots a summary of the imbalances in a W_base_object object
Prints a summary of a optimal_rerandomization_obj object
Prints a summary of a W_base_object object
Prints a summary of a optimal_rerandomization_obj object
Prints a summary of a W_base_object object
This is a tool to find the optimal rerandomization threshold in non-sequential experiments. We offer three procedures based on assumptions made on the residuals distribution: (1) normality assumed (2) excess kurtosis assumed (3) entire distribution assumed. Illustrations are included. Also included is a routine to unbiasedly estimate Frobenius norms of variance-covariance matrices. Details of the method can be found in "Optimal Rerandomization via a Criterion that Provides Insurance Against Failed Experiments" Adam Kapelner, Abba M. Krieger, Michael Sklar and David Azriel (2020) <arXiv:1905.03337>.