plotAGV: Adversarial Group Calibration based on the Scal statistic

In ppernot/ErrViewLib: Library for ErrView

Adversarial Group Calibration based on the Scal statistic

Description

Adversarial Group Calibration based on the Scal statistic

Usage

plotAGV(
  Z,
  popMin = 50,
  nGroup = 100,
  nMC = 500,
  add = FALSE,
  ylim = NULL,
  col = 6,
  control = TRUE,
  colControl = 2,
  stat = c("max", "mean", "median", "q95"),
  dist = c("Normal", "Uniform", "Normpn", "Normp4", "Laplace", "T4", "Student"),
  df = 4,
  title = "",
  label = 0,
  legend = TRUE,
  gPars = ErrViewLib::setgPars()
)

Arguments

Z	(vector) set of z-score values to be tested
popMin	(integer) minimal bin count in an interval
nGroup	(integer) number random groups sampled to select worst one
nMC	(integer) number of repeats for worst group selection
add	(logical) add to previous graph ?
ylim	(vector) limits of the y axis
col	(integer) color index of main curve
control	(logical) estimate AGV for control sample (normal-standard)
colControl	(integer) color index of control curve
dist	(string) model error distribution to generate the control values. One of 'Normal' (default), 'Uniform', 'Normpn', Normp4', 'Laplace', 'Tn' or 'T4'
df	(integer) degrees of freedom for distributions 'Normpn' and 'Tn'
title	(string) a title to display above the plot
label	(integer) index of letter for subplot tag
legend	(logical) add a legend (default: TRUE) ?
gPars	(list) graphical parameters
method	(string) method used to estimate 95 percent CI on <Z^2>

Value

Nothing.

Examples

  uE  = sqrt(rchisq(1000, df = 4))  # Re-scale uncertainty
  E   = rnorm(uE, mean=0, sd=uE)    # Generate errors
  plotAGV(E/uE)

ppernot/ErrViewLib documentation built on June 1, 2024, 4:33 a.m.