Skip to contents

Plot p-values and implied rejection boundaries

plot_p.Rd

Creates a plot of the p-values and implied rejection boundaries on a grid of values for the first and second-stage test statistics.

Usage

plot_p(
  estimator,
  data_distribution,
  design,
  mu = 0,
  sigma,
  boundary_color = "lightgreen",
  subdivisions = 100,
  ...
)

Arguments

estimator

object of class PointEstimator, IntervalEstimator or PValue.

data_distribution

object of class Normal or Student.

design

object of class TwoStageDesign.

mu

expected value of the underlying normal distribution.

sigma

assumed standard deviation.

boundary_color

color of the implied rejection boundary.

subdivisions

number of subdivisions per axis for the grid of test statistic values.

...

additional arguments handed down to ggplot

Value

a ggplot object visualizing the p-values on a grid of possible test-statistic values.

Details

When the first-stage test statistic lies below the futility threshold (c1f) or above the early efficacy threshold (c1e) of the TwoStageDesign, there is no second-stage test statistics. The p-values in these regions are only based on the first-stage values. For first-stage test statistic values between c1f and c1e, the first and second-stage test statistic determine the p-value.

The rejection boundary signals the line where

Examples

plot_p(estimator = StagewiseCombinationFunctionOrderingPValue(),
  data_distribution = Normal(FALSE),
  design = get_example_design(),
  mu = 0,
  sigma = 1)