verboseScatterplot: Scatterplot annotated by regression line and p-value

Description

Produce a scatterplot annotated by the correlation, p-value, and regression line.

Usage

verboseScatterplot(x, y, 
                   sample = NULL,
                   corFnc = "cor", corOptions = "use = 'p'", 
                   main = "", xlab = NA, ylab = NA, 
                   cex = 1, cex.axis = 1.5, cex.lab = 1.5, cex.main = 1.5, 
                   abline = FALSE, abline.color = 1, abline.lty = 1,
                   corLabel = corFnc, 
                   displayAsZero = 1e-5,
                   col = 1, bg = 0, pch = 1,
                   lmFnc = lm,
                   plotPriority = NULL,
                   showPValue = TRUE,
                   ...)

Value

If sample above is given, the indices of the plotted points are returned invisibly.

Arguments

x: numerical vector to be plotted along the x axis.
y: numerical vector to be plotted along the y axis.
sample: determines whether x and y should be sampled for plotting, useful to keep the plot manageable when x and y are large vectors. The default NULL value implies no sampling. A single numeric value will be interpreted as the number of points to sample randomly. If a vector is given, it will be interpreted as the indices of the entries in x and y that should be plotted. In either case, the correlation and p value will be determined from the full vectors x and y.
corFnc: character string giving the correlation function to annotate the plot.
corOptions: character string giving further options to the correlation function.
main: main title for the plot.
xlab: label for the x-axis.
ylab: label for the y-axis.
cex: character expansion factor for plot annotations, recycled as necessary.
cex.axis: character expansion factor for axis annotations.
cex.lab: character expansion factor for axis labels.
cex.main: character expansion factor for the main title.
abline: logical: should the linear regression fit line be plotted?
abline.color: color specification for the fit line.
abline.lty: line type for the fit line.
corLabel: character string to be used as the label for the correlation value printed in the main title.
displayAsZero: Correlations whose absolute value is smaller than this number will be displayed as zero. This can result in a more intuitive display (for example, cor=0 instead of cor=2.6e-17).
col: color of the plotted symbols. Recycled as necessary.
bg: fill color of the plotted symbols (used for certain symbols). Recycled as necessary.
pch: Integer code for plotted symbols (see link{plot.default}). Recycled as necessary.
lmFnc: linear model fit function. Used to calculate the linear model fit line if 'abline' is TRUE. For example, robust linear models are implemented in the function rlm.
plotPriority: Optional numeric vector of same length as x. Points with higher plot priority will be plotted later, making them more visible if points overlap.
showPValue: Logical: should the p-value corresponding to the correlation be added to the title?
...: other arguments to the function plot.

Author

Steve Horvath and Peter Langfelder

Details