Represents the randomization procedure Chen's Design.
Usage
chenPar(N, mti = N, p = 0.5, groups = LETTERS[1:2])
Arguments
N
integer for the total sample size of the trial.
mti
maximum tolerated imbalance in patient numbers during the trial.
p
success probability of the biased coin (e.g. in Efron's Biased Coin
Design).
groups
character vector of labels for the different treatments.
Details
Flip a biased coin with probability p in favour of the treatment
which is allocated less frequently as long as the difference in group sizes doesn't
exceed the mti. If the mti is reached a deterministic
allocation is done, so that the difference in group sizes is reduced.
If both treatments have been assigned equally often a fair coin is tossed.
Value
S4 object of the class chenPar.
References
Chen Yung-Pin (1999) Biased coin design with imbalance tolerance.
Comm. in Stat., 15, 953-975.