mulitpleTestingCorrections.plotPvalDistrib: Multiple corrections for multiple testing

In jvanheld/stats4bioinfo: Utilities for the book "Statistics for bioinformatics"

Description

Generate a plot that reproduces Fig 1 from Storey and Tibshirani (2003), with some additional details, in order to illustrate the estimation of the parameter PI0 = m0/m1.

Usage

mulitpleTestingCorrections.plotPvalDistrib(multitest.result,
  main = "P-value distribution", plot.legend = TRUE, legend.cex = 1,
  legend.corner = "topright", breaks = seq(from = 0, to = 1, by = 0.05),
  draw.lambda = "arrow", draw.m0.line = TRUE, draw.mean.line = TRUE,
  overlay = NULL, col = "#FFEEDD", overlay.col = "#CCCCCC",
  mean.line.col = "darkred", m0.line.col = "blue", ...)

Arguments

multitest.result	the list returned by the function multipleTestingCorrections().
...	Additional parameters are passed to hist()
main='Multitesting	corrections' main title of the plot
plot.legend=TRUE	Plot a legend with some indicative numbers (m0, m1, pi0).
legend.corner="topright"	corner wher the legend has to be placed.
legend.cex=1	Font size for the legend.
breaks=seq(from=0, to=1,	by=0.05) Breaks for the histogram
draw.lambda="arrow"	Indicate the level of the lambda parameter. Supported representations: "arrow", "line", "none".
draw.m0.line=TRUE	Draw an horizontal line indicating the estimated m0 (number of trully null features) per bin.
draw.mean.line=FALSE	Draw a dashed horizontal line indicating the mean number of features per bin. The difference between this line and the "m0 per bin" line reflects the importance of truly alternative features.
col="#BBBBFF"	Histogram background color (passed to hist()).
overlay=NULL	Boolean vector marking features of a special category (e.g. truly null features). A colored histogram will be printed on top of the main histogram, to indicate the number of features belonging to this group.
overlay.col="#CCCCCC"	Color for the overlay histogram.
mean.line.col="black"	Color to draw the line indicating the mean number of feature per bin.
m0.line.col="black"	Color to draw the line indicating the estimated m0 per bin.

Author(s)

Jacques van Helden ([e-mail])

Examples

## To obtain the input list (multitest.result), run the examples of
## stats4bioinfo::multipleTestingCorrections().

example(multipleTestingCorrections)

## Plot the p-value distribution + landmarks
mulitpleTestingCorrections.plotPvalDistrib(multitest.result, draw.lambda="line")

jvanheld/stats4bioinfo documentation built on May 20, 2019, 5:16 a.m.