OneArmPhaseTwoStudy (version 1.0.3)

getSolutions: Returns designs for a given "simon"-object (see setupSimon)

Description

getSolutions uses a "simon"-object to calculate two-stage designs as they were described by Simon.

Usage

getSolutions(simon = setupSimon(), useCurtailment = FALSE,
  curtail_All = FALSE, cut = 0, replications = 10000, upperBorder = 0)

Arguments

simon

a "simon"-object which will be used to calculate designs.

useCurtailment

boolean value determining whether (non-)stochastic curtailment is used.

curtail_All

boolean value; if true the effect of (non-)stochastic curtailment will be calculated for different cut points in 0.05 steps starting with the value of the parameter "cut".

cut

sets the "cut point" used to calculate the effect of (non-)stochastic curtailment. A study is stopped if the conditional power falls below the value of "cut".

replications

number of simulations to estimate the effect of (non-)stochastic curtailment.

upperBorder

maximal possible value for n. If set to sero (default) the programm will aproximate a upper border automaticly.

References

Simon, R. (1989): Optimal two-stage designs for phase II clinical trials. Controlled Clinical Trials 10,1-10.

Kunz C.U., Kieser M (2012): Curtailment in single-arm two-stage phase II oncology trials. Biometrical Journal 54, 445-456

See Also

setupSimon

Examples

# NOT RUN {
# Example 1: Using the default values
designs <- getSolutions()
designs <- designs$Solutions
designs
# }
# NOT RUN {
# Example 2: Setting up a "simon"-object, then calculate designs
simon <- setupSimon(alpha = 0.1, beta = 0.2, p0 = 0.3, p1 = 0.5)
designs <- getSolutions(simon)$Solutions
designs

# Esample 3: Calculating designs and simulating the influence of
# stochastic curtailment for each design.
simon <- setupSimon(alpha = 0.1, beta = 0.2, p0 = 0.3, p1 = 0.5)
designs <- getSolutions(simon, useCurtailment = TRUE, curtail_All = TRUE, cut = 0.3)
#List containing the found designs, the influence of stochastic curtailment
# and the regarding stopping rules.
designs
# }