Generic function for optimizing multi-arm programs
optimal_multiarm_generic(
n2min,
n2max,
stepn2,
beta,
alpha,
c2,
c3,
c02,
c03,
K,
N,
S,
b1,
b2,
b3,
strategy,
num_cl
)minimal total sample size in phase II, must be divisible by 3
maximal total sample size in phase II, must be divisible by 3
stepsize for the optimization over n2, must be divisible by 3
type-II error rate for any pair, i.e. 1 - beta is the (any-pair) power for calculation of the sample size for phase III
one-sided significance level/family-wise error rate
variable per-patient cost for phase II
variable per-patient cost for phase III
fixed cost for phase II
fixed cost for phase III
constraint on the costs of the program, default: Inf, e.g. no constraint
constraint on the total expected sample size of the program, default: Inf, e.g. no constraint
constraint on the expected probability of a successful program, default: -Inf, e.g. no constraint
expected gain for effect size category "small"
expected gain for effect size category "medium"
expected gain for effect size category "large"
choose strategy: 1 (only the best promising candidate), 2 (all promising candidates) or 3 (both strategies)
number of clusters used for parallel computing, default: 1