plot.bootstrap: Plotting Bootstrap Equating Results

Description

This function plots bootstrap equating results for objects of class “bootstrap”.

Usage

# S3 method for bootstrap
plot(
  x,
  add = FALSE,
  out = "mean",
  xpoints,
  ypoints,
  addident = TRUE,
  identy,
  identcol = 1,
  rescale = c(0, 1),
  xlab = "Total Score",
  ylab,
  col = rainbow(length(x$args)),
  pch,
  lty = 1,
  subset,
  morepars = NULL,
  addlegend = TRUE,
  legendtext,
  legendplace = "bottomright",
  ...
)

Arguments

x: output from the bootstrap function.
add: logical, with default FALSE, specifying whether to create a new plot or add to the current one.
out: character vector specifying the output to be plotted, either the mean equated scores ("mean"), standard errors ("se"), bias ("bias"), or RMSE ("rmse").
xpoints, ypoints: optional vectors of the same length containing raw scores on forms X and Y, assuming a single group or equivalent groups design.
addident: logical, with default TRUE, for plotting the identity function. The result depends on out.
identy: vector of y coordinates for plotting the identity line. Defaults to the identity function when out = "eqs", otherwise, a horizontal line with intercept 0.
identcol: color used for plotting the identity line.
rescale: intercept and slope, with default 0 and 1, used to rescale all lines before plotting.
xlab, ylab, col, pch, lty: graphical parameters passed to par, with the lengths of col and lty recycled as necessary.
subset: vector for subsetting the output when multiple equating functions are included in x.
morepars: list of additional graphical parameters, excluding xlab, ylab, col, pch, lty.
addlegend: logical, with default TRUE, indicating whether or not a legend should be added.
legendtext: character vector of text to be passed to the legend argument of the legend function, defaulting to a combination of the equating types and methods specified in each equating object.
legendplace: placement of the legend.
...: further arguments passed to or from other methods, excluding graphical parameters.

Author

Anthony Albano tony.d.albano@gmail.com

Details

Lines are plotted for the chosen output type, whether mean equated scores across replications (out = "mean"), standard errors (out = "se"), bias (out = "bias") or RMSE (out = "rmse"). The result is similar to that of plot.equate.

Examples

Run this code


set.seed(122713)
neat.x <- freqtab(KBneat$x, scales = list(0:36, 0:12))
neat.y <- freqtab(KBneat$y, scales = list(0:36, 0:12))
eqargs <- list(m.t = list(type = "mean", method = "t"),
  l.t = list(type = "lin", method = "t"),
	c.t = list(type = "circ", method = "t"))
bootout <- bootstrap(x = neat.x, y = neat.y, args = eqargs,
	reps = 20)
plot(bootout, out = "se", legendplace = "top")