des_gs_bern: Design a multi-stage group-sequential multi-arm clinical...

In mjg211/multiarm: Design of single- and multi-stage multi-arm clinical trials

Design a multi-stage group-sequential multi-arm clinical trial for a Bernoulli distributed primary outcome

Description

des_gs_bern() determines multi-stage group-sequential multi-arm clinical trial designs assuming the primary outcome variable is Bernoulli distributed. It computes required design components and returns information on key operating characteristics.

Usage

des_gs_bern(
  K = 2,
  J = 2,
  alpha = 0.025,
  beta = 0.1,
  pi0 = 0.3,
  delta1 = 0.2,
  delta0 = 0,
  ratio = 1,
  power = "marginal",
  stopping = "simultaneous",
  type = "variable",
  fshape = "pocock",
  eshape = "pocock",
  ffix = -3,
  efix = 3,
  spacing = (1:J)/J,
  integer = FALSE,
  summary = FALSE
)

Arguments

K	A numeric indicating the chosen value for K, the (initial) number of experimental treatment arms. Defaults to 2.
J	A numeric indicating the chosen value for J, the (maximum) number of allowed stages. Defaults to 2.
alpha	A numeric indicating the chosen value for α, the significance level (family-wise error-rate). Defaults to 0.025.
beta	A numeric indicating the chosen value for β, used in the definition of the desired power. Defaults to 0.1.
pi0	A numeric indicating the chosen value for π0, the response rate in the control arm. Defaults to 0.3.
delta1	A numeric indicating the chosen value for δ1, the 'interesting' treatment effect. Defaults to 0.5.
delta0	A numeric indicating the chosen value for δ0, the 'uninteresting' treatment effect. Defaults to 0.
ratio	A numeric indicating the chosen value for r, the stage-wise allocation ratio to present experimental arms. Defaults to 1.
power	A character string indicating the chosen type of power to design the trial for. Can be "disjunctive" or "marginal". Defaults to "marginal".
stopping	A character string indicating the chosen type of stopping rule. Can be "separate" or "simultaneous". Defaults to "simultaneous".
type	A character string indicating the choice for the stage-wise sample size. Can be "variable" or "fixed". Defaults to "variable".
fshape	A character string indicating the choice for the futility (lower) stopping boundaries. Can be any of "fixed", "obf", "pocock", and "triangular". Defaults to "pocock".
eshape	A character string indicating the choice for the efficacy (upper) stopping boundaries. Can be any of "fixed", "obf", "pocock", and "triangular". Defaults to "pocock".
ffix	A numeric indicating the chosen value for the fixed interim futility bounds. Only used when fshape = "fixed". Defaults to "-3".
efix	A numeric indicating the chosen value for the fixed interim efficacy bounds. Only used when eshape = "fixed". Defaults to "3".
spacing	A numeric vector indicating the chosen spacing of the interim analyses in terms of the proportion of the maximal possible sample size. It must contain strictly increasing values, with final element equal to 1. Defaults to (1:J)/J (i.e., to equally spaced analyses).
integer	A logical variable indicating whether the computed possible sample sizes required in each arm in each stage should be forced to be whole numbers. Defaults to FALSE. WARNING: If you set integer = TRUE and ratio != 1, obscure results can occur due to difficulties in identifying a suitable whole number sample size that meets the allocation ratio requirement.
summary	A logical variable indicating whether a summary of the function's progress should be printed to the console. Defaults to FALSE.

Value

A list, with additional class "multiarm_des_gs_bern", containing the following elements:

• A tibble in the slot $opchar summarising the operating characteristics of the identified design.

• A tibble in the slot $pmf_N summarising the probability mass function of the random required sample size under key scenarios.

• A numeric vector in the slot $e specifying e, the trial's efficacy (upper) stopping boundaries.

• A numeric vector in the slot $f specifying f, the trial's futility (lower) stopping boundaries.

• A numeric in the slot $maxN specifying max N, the trial's maximum required sample size.

• A numeric in the slot $n_factor, for internal use in other functions.

• A numeric in the slot $n1 specifying n₁, the total sample size required in stage one of the trial.

• A numeric in the slot $n10 specifying n₁₀, the sample size required in the control arm in stage one of the trial.

• Each of the input variables.

See Also

build_gs_bern, gui, opchar_gs_bern, plot.multiarm_des_gs_bern, sim_gs_bern.

Examples

# The design for the default parameters
des <- des_gs_bern()

mjg211/multiarm documentation built on Jan. 19, 2024, 8:21 a.m.