README.md

In jtextor/trialMinRand: Minimisation Randomization for Clinical Trials

trialMinRand

This is a barebone, no-frills R package that implements a minimization randomization algorithm for clinical trials. The package implements minimization as described in:

Pocock, Stuart J.; Simon, Richard: Sequential Treatment Assignment with Balancing for Prognostic Factors in the Controlled Clinical Trial. Biometrics, 31(1):103-115, 1975. https://dx.doi.org/10.2307/2529712

Example

This is a basic example which shows you how to solve a common problem:

# Define patient data
d <- data.frame( F1=factor(c(1,2,2),levels=1:2),
  F2=factor(c(1,1,2),levels=1:2) )

# Define previous treatments
tr <- c("A","A")

# Define desired ratio for all possible treatments: A:B=2:1
tratio <- c(A=2,B=1)

# Call function to obtain next treatment. With probability 
# 0.7, this is going to be a treatment that minimizes imbalance.
# With probability 0.3, it is going to be a random treatment.
# Both imbalance and the distribution of random treatments are 
# defined using a 2:1 ratio for the treatments A and B.
next.tr <- assign.next.treatment( d, tratio, tr, p=0.3 )

jtextor/trialMinRand documentation built on July 29, 2023, 8:59 a.m.