modelplot: Plot results of t-test, ANOVA or TANOVA modeling functions
In tdeenes/eegR: Analyze EEG Signals

Description Usage Arguments Value Methods (by class) See Also

modelplot is a generic function for plotting arrayTtest, arrayAnova, or tanova objects, each produced by the corresponding function.

modelplot.default plots the result of the arrayTtest or arrayAnova function.

modelplot.tanova plots the result of the tanova function.

modelplot(...)

## Default S3 method:
modelplot(
  results,
  what = c("statistic", "p-value"),
  type = c("corrected", "uncorrected"),
  pcrit = c(0.001, 0.01, 0.05),
  grid = NULL,
  wrap = NULL,
  time_label = "Time (ms)",
  channel_label = "Channels",
  raster = TRUE,
  cluster_order = FALSE,
  low = scales::muted("blue"),
  mid = "white",
  high = scales::muted("red"),
  midpoint = 0,
  ...
)

## S3 method for class 'tanova'
modelplot(
  results,
  what = c("statistic", "p-value"),
  type = c("corrected", "uncorrected"),
  grid = NULL,
  wrap = NULL,
  time_label = "Time (ms)",
  ...
)

`...`	arguments passed to `extract`; e.g. use arguments 'time_window' and 'term' to display only a subset of the results
`results`	a list; the return value of the corresponding modeling functions
`what`	a character string or vector indicating what should be plotted: only the test statistics ("statistic"), only the p-values ("p-values"), or both (default). The names can be abbreviated.
`type`	display "corrected" (default) or "uncorrected" statistics or p-values. The names can be abbreviated.
`pcrit`	numeric vector of significancy limits (default: 0.001, 0.01, 0.05) for highlighting significant areas
`grid`	character vector or formula defining the layout of panels
`wrap`	character vector or formula defining the dimension which separates panels (only considered if grid is NULL)
`time_label`	character string; the label of the x (time) axis (default: "Time (ms)")
`channel_label`	character string; the label of the y (channel) axis default: "Channels")
`raster`	use raster image (TRUE, default) or not (FALSE)
`cluster_order`	logical; if TRUE, channels are ordered with hierarchical agglomerative clustering (default: FALSE)
`low`	colour for low/mid/high end of gradient, respectively
`mid`	colour for low/mid/high end of gradient, respectively
`high`	colour for low/mid/high end of gradient, respectively
`midpoint`	the midpoint (in data value) of the diverging scale (default: 0)