plot.smacofP {stops}

S3 plot method for smacofP objects

Description

S3 plot method for smacofP objects

Usage

## S3 method for class 'smacofP'
plot(
  x,
  plot.type = "confplot",
  plot.dim = c(1, 2),
  bubscale = 5,
  col,
  label.conf = list(label = TRUE, pos = 3, col = 1, cex = 0.8),
  identify = FALSE,
  type = "p",
  pch = 20,
  asp = 1,
  main,
  xlab,
  ylab,
  xlim,
  ylim,
  legend = TRUE,
  legpos,
  loess = TRUE,
  ...
)

Arguments

x

an object of class smacofP

plot.type

String indicating which type of plot to be produced: "confplot", "resplot", "Shepard", "stressplot","transplot", "bubbleplot" (see details)

plot.dim

dimensions to be plotted in confplot; defaults to c(1, 2)

bubscale

Scaling factor (size) for the bubble plot

col

vector of colors for the points

label.conf

List with arguments for plotting the labels of the configurations in a configuration plot (logical value whether to plot labels or not, label position, label color)

identify

If 'TRUE', the 'identify()' function is called internally that allows to add configuration labels by mouse click

type

What type of plot should be drawn (see also 'plot')

pch

Plot symbol

asp

Aspect ratio; defaults to 1 so distances between x and y are represented accurately; can lead to slighlty weird looking plots if the variance on one axis is much smaller than on the other axis; use NA if the standard type of R plot is wanted where the ylim and xlim arguments define the aspect ratio - but then the distances seen are no longer accurate

main

plot title

xlab

label of x axis

ylab

label of y axis

xlim

scale of x axis

ylim

scale of y axis

legend

Flag whether legends should be drawn for plots that have legends

legpos

Position of legend in plots with legends

loess

should loess fit be added to Shepard plot

...

Further plot arguments passed: see 'plot.smacof' and 'plot' for detailed information.

Details

• Configuration plot (plot.type = "confplot"): Plots the MDS configurations.

• Residual plot (plot.type = "resplot"): Plots the dissimilarities against the fitted distances with a linear regression line (without an intercept as in ratio MDS).

• Linearized Shepard diagram (plot.type = "Shepard"): Diagram with the transformed observed dissimilarities against the transformed fitted distance as well as loess curve and a least squares line. The fitted lines do not have an intercept.

• Transformation Plot (plot.type = "transplot"): Diagram with the observed dissimilarities (lighter) and the transformed observed dissimilarities (darker) against the fitted distances together with the nonlinear regression curve (no intercept). Works for lmds or bcStress models too, but is somewhat nonsensical due to them being energy models.

• Stress decomposition plot (plot.type = "stressplot"): Plots the stress contribution in of each observation. Note that it rescales the stress-per-point (SPP) from the corresponding smacof function to percentages (sum is 100). The higher the contribution, the worse the fit. Only implemented for models from the classical stress world, not for bcmds or lmds (throws an error).

• Bubble plot (plot.type = "bubbleplot"): Combines the configuration plot with the point stress contribution. The larger the bubbles, the better the fit.Only implemented for models from the classical stress world, bcmds or lmds (throws an error).

Value

no return value; just plot for class 'smacofP' (see details)