Skip to contents

Randomization of Subjects in two arm designs

Shubham Lahoti

September 26, 2024

PatientRandomization.Rmd

Introduction :

In the RCode directory of this example you will find the following R files:

  1. RandomizationSubjectsUsingUniformDistribution.R

The R function named “RandomizationSubjectsUsingUniformDistribution” in the file randomly allots the subjects on either of two arms using Uniform Distribution.

Steps : 1) We generate a random number from Uniform(0, 1). Save it as u. 2) Let p = Allocation fraction on Control arm and 1 - p = Allocation fraction on treatment arm. 3) If u <= p then allot the subject to Control arm else allot the subject to treatment arm. 4) Make sure that Total sample size = Sample size on control + Sample size on treatment arm.

  1. RandomizationSubjectsUsingSampleFunctionInR.R

The R function named “RandomizationSubjectsUsingSampleFunctionInR” in the file makes use of Sample() function in R to randomly allot the patients on Control and treatment arm.

Steps:

  1. Let p = Allocation fraction on Control arm and 1 - p = Allocation fraction on treatment arm.
  2. Compute Expected Sample size (rounded) for Control and treatment arms using Allocation Fraction and Total sample size.
  3. Randomly allot the indices to Control and treatment arms using sample() functionality available in R.
  4. Create a vector of zeroes of size = NumSub (Number of subjects) and then replace the zeroes by 1 for the Indices that correspond to treatment.
  1. BlockRandomizationSubjectsUsingRPackage.R

The function named “BlockRandomizationSubjectsUsingRPackage.R” in the file makes use of pbrPar() function from the library named “randomizeR” to perform the Block randomization.

Description:

Imbalances between groups can be minimized in small sample–size studies by restricting the randomization procedure. Restricted randomization means that randomization is applied in a manner that helps ensure the desired proportions of treatment groups, beyond random chance, within defined groups of patients.

The permuted block technique randomizes patients between groups within a set of study participants, called a block. Treatment assignments within blocks are determined so that they are random in order but that the desired allocation proportions are achieved exactly within each block.

  1. LoadrandomizeR.R

This file is used to install the “randomizeR” package for execution of Block Randomization in R.