fastrerandomize - Fast Rerandomization Using Accelerated Computing

fastrerandomize Released!

Our new R package leverages GPU acceleration and parallel processing to make rerandomization feasible for large-scale experiments with complex balance requirements.

Read the accompanying package paper here.

Features

Designed to make rerandomization accessible for experimental designs at any and all scales.

Accelerated Computation

Employs batched processing, autovectorization, just-in-time-compilation, and (optionally) GPU acceleration to dramatically improve performance (>50x compared to traditional methods).

Learn more

Scale to Any Size

Allows for use in cases where the sample size or number of covariates is very large, making rerandomization practical for modern, large-scale experiments.

Open-Source

Distributed under a GPL-3 license, fastrerandomize is developed and maintained publicly on GitHub.

Balanced Assignment

Generates pools of acceptable randomizations based on a given acceptance probability, ensuring optimal covariate balance across treatment groups.

Tests and Thresholds

Conducts exact rerandomization tests and computes optimal rerandomization acceptance thresholds for reliable statistical inference.

Real-world Applications

Speed ups in applications to economic and geographical experiments, making complex designs accessible to practitioners.

View applications

Example Use

# Step 1: Set up the environment
library(fastrerandomize)

# Build the backend with Python dependencies
build_backend(
  conda_env = "fastrerandomize", 
  conda = "auto"
)

# Step 2: Create some example covariate data
set.seed(999L)
n <- 1000
X <- matrix(rnorm(n * 5), n, 5)

# Step 3: Generate balanced treatment assignments using the main function
result <- generate_randomizations(
  n_units = n,
  n_treated = n/2,    # Number of treated units (50%)
  X = X,              # Covariate matrix
  randomization_accept_prob = 0.01,  # Acceptance probability
  randomization_type = "monte_carlo"  # Use Monte Carlo sampling
)

# Examine the results
head(result$randomizations)  # Treatment assignments
summary(result$balance)      # Balance statistics
plot(result)                 # Plot distribution of balance measures
        

# Advanced Monte Carlo Batching
library(fastrerandomize)

# Create example data with many covariates
set.seed(42)
n <- 5000
p <- 20
X <- matrix(rnorm(n * p), n, p)

# For large datasets, use monte_carlo explicitly
result_mc <- generate_randomizations_mc(
  n_units = n,
  n_treated = n/2,
  X = X,
  randomization_accept_prob = 0.001,  # Stricter balance criterion
  max_draws = 1e6,       # Maximum number of randomizations to draw
  batch_size = 10000,    # Process in batches for memory efficiency
  approximate_inv = TRUE # Use diagonal approximation for speed
)

# For faster computation with GPU acceleration
# Especially useful for large datasets
gpu_result <- generate_randomizations(
  n_units = n,
  n_treated = n/2,
  X = X,
  randomization_accept_prob = 0.0001,  # Very stringent
  max_draws = 1e6,
  batch_size = 10000,
  randomization_type = "monte_carlo",
  verbose = TRUE        # Show progress information
)
        

# Using the randomization test functionality
library(fastrerandomize)

# 1. Generate covariates
set.seed(123)
n <- 100
X <- matrix(rnorm(n * 3), n, 3)

# 2. Generate candidate randomizations
randomizations <- generate_randomizations(
  n_units = n,
  n_treated = n/2,
  X = X,
  randomization_accept_prob = 0.05,
  randomization_type = "monte_carlo",
  max_draws = 10000,
  batch_size = 1000
)

# 3. Generate a simulated outcome with known effect
obsW <- randomizations$randomizations[1,]  # Use first randomization
true_effect <- 0.5                        # True treatment effect
obsY <- rnorm(n) + obsW * true_effect

# 4. Conduct randomization test
test_result <- randomization_test(
  obsW = obsW,
  obsY = obsY,
  X = X,
  candidate_randomizations = randomizations$randomizations,
  findFI = TRUE,   # Calculate fiducial interval
  alpha = 0.05     # Significance level
)

# 5. Examine test results
print(test_result)
plot(test_result)  # Visualize effect and fiducial interval
        

Research & Citations

For more information, see the package paper: Connor T. Jerzak, Rebecca Goldstein, Aniket Kamat, Fucheng Warren Zhu. "fastrerandomize: An R Package for Fast Rerandomization Using Accelerated Computing," 2025.