
Last chance! 50% off unlimited learning
Sale ends in
A shift plot is a plot of the quantiles of a data set y minus those of another data set x against those of x. Includes 95 percent simultaneous confidence bands.
shiftplot(x, y, pch = 20, xlab = "x Quantiles", ylab = "y Quantiles", main = NULL, ...)
numeric vector of length m.
numeric vector of length n.
Plotting character.
Character string giving abscissa axis label.
Character string giving ordinate axis label.
Character string giving plot title.
Other optional arguments to plot function.
No value is returned, but a plot is created.
The shift plot is a graph of y_q - x_q vs. x_q, where y_q and x_q denote the quantiles of x and y, resp. 95 percent simultaneous confidence bands are calculated per Doksum and Sievers (1976). The primary usage of this plot is where x is a control group and y is an experimental method; or something similar. For example, x might represent observations, and y might represent climate model output; or some such.
Doksum, K. A. and Sievers, G. L. (1976) Plotting with confidence: graphical comparisons of two populations. Biometrika, 63, (3), 421--434.
# NOT RUN {
z <- rnorm( 100)
y <- rexp(30)
shiftplot( z, y)
data( ftcanmax)
shiftplot( y, ftcanmax[,"Prec"])
# }
Run the code above in your browser using DataLab