ErrViewLib: Library for ErrView

plotLZMS

R Documentation

Plot local Mean Squared z-score <Z^2> to assess calibration and tightness

Description

Plot local Mean Squared z-score <Z^2> to assess calibration and tightness

Usage

plotLZMS(
  X,
  Z,
  aux = NULL,
  varZ = 1,
  logX = FALSE,
  nBin = NULL,
  equiPop = TRUE,
  popMin = 100,
  logBin = TRUE,
  intrv = NULL,
  plot = TRUE,
  slide = FALSE,
  nBoot = 5000,
  parallel = FALSE,
  method = c("bootstrap", "stud", "auto"),
  BSmethod = c("bca", "perc", "basic", "stud"),
  xlab = "Conditioning variable",
  skewup = 0.8,
  xlim = NULL,
  ylim = NULL,
  title = "",
  score = FALSE,
  add = FALSE,
  col = 5,
  colInv = 2,
  label = 0,
  gPars = ErrViewLib::setgPars()
)

Arguments

`X`	(vector) abscissae of the Z values
`Z`	(vector) set of z-score values to be tested
`aux`	(vector) auxilliary vector to resolve ties in X sorting
`varZ`	(numeric) target value for Var(Z) (default '1')
`logX`	(logical) log-transform X
`nBin`	(integer) number of intervals for local coverage stats
`equiPop`	(logical) generate intervals with equal bin counts (default: 'equiPop = TRUE')
`popMin`	(integer) minimal bin count in an interval
`logBin`	(logical) if 'equiPop = FALSE', one can choose between equal range intervals, or equal log-range intervals (default 'logBin = TRUE')
`intrv`	(object) intervals generated by 'genIntervals' (default: 'NULL')
`plot`	(logical) plot the results
`slide`	(logical) use sliding window for subsetting (X,Z)
`nBoot`	(integer) number of bootstrap replicas
`parallel`	(logical) parallelized bootstrap (default: 'FALSE')
`method`	(string) method used to estimate 95 percent CI on <Z^2>
`BSmethod`	(string) bootstrap variant
`xlab`	(string) X axis label
`skewup`	(numeric) upper limit for robust skewness of Z^2, used for reliability estimation (defaul: 0.8). The unreliable results are grayed out. Set to NULL to inactivate this check.
`xlim`	(vector) min and max values of X axis
`ylim`	(vector) limits of the y axis
`title`	(string) a title to display above the plot
`score`	(logical) estimate calibration stats (default: 'FALSE')
`add`	(logical) add to previous graph ?
`col`	(integer) color index of bin stats
`colInv`	(integer) color index of invalid bin stats
`label`	(integer) index of letter for subplot tag
`gPars`	(list) graphical parameters

Value

Invisibly returns a list of LZMS results. Mainly used for its plotting side effect.

Examples


  uE  = sqrt(rchisq(1000, df = 4))  # Re-scale uncertainty
  E   = rnorm(uE, mean=0, sd=uE)    # Generate errors
  plotLZMS(uE, E/uE, method = 'cho', ylim = c(0,2))

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