Transformation Axes {car}R Documentation

Axes for Transformed Variables

Description

These functions produce axes for the original scale of transformed variables. Typically these would appear as additional axes to the right or at the top of the plot, but if the plot is produced with axes=FALSE, then these functions could be used for axes below or to the left of the plot as well.

Usage

power.axis(power, base=exp(1), side=c("right", "above", "left", "below"), 
  at, grid=FALSE, grid.col=gray(0.5), grid.lty=3, 
  axis.title="Untransformed Data", cex=1, las=par("las"))

box.cox.axis(power, side=c("right", "above", "left", "below"), 
  at, grid=FALSE, grid.col=gray(0.5), grid.lty=3, 
  axis.title="Untransformed Data", cex=1, las=par("las"))

prob.axis(at, side=c("right", "above", "left", "below"), grid=FALSE, grid.lty=3, 
  grid.col=gray(0.5), axis.title="Probability", interval=0.1, cex=1, las=par("las"))

Arguments

power power for Box-Cox or power transformation.
side side at which the axis is to be drawn; numeric codes are also permitted: side = 1 for the bottom of the plot, side=2 for the left side, side = 3 for the top, side = 4 for the right side.
at numeric vector giving location of tick marks on original scale; if missing, the function will try to pick nice locations for the ticks.
grid if TRUE grid lines for the axis will be drawn.
grid.col color of grid lines.
grid.lty line type for grid lines.
axis.title title for axis.
cex relative character expansion for axis label.
las if 0, ticks labels are drawn parallel to the axis; set to 1 for horizontal labels (see par).
base base of log transformation for power.axis when power = 0.
interval desired interval between tick marks on the probability scale.

Details

The transformations corresponding to the three functions are as follows:

power.axis:
x' = x^p for p != 0 and x' = log x for p = 0.
box.cox.axis:
x' = (x^p - 1)/p for x != 0 and x' = log(x) for p = 0.
prob.axis:
logit = log[p/(1 - p)].

These functions will try to place tick marks at reasonable locations, but producing a good-looking graph sometimes requires some fiddling with the at argument.

Value

These functions are used for their side effects: to draw axes.

Author(s)

John Fox jfox@mcmaster.ca

See Also

box.cox, logit

Examples

UN<-na.omit(UN)
attach(UN)
par(mar=c(5, 4, 4, 4)+.1)

plot(log(gdp, 10), log(infant.mortality, 10))
power.axis(0, base=10, side="above", 
  at=c(50,200,500,2000,5000,20000),grid=TRUE, axis.title="GDP per capita")
power.axis(0, base=10, side="right",
  at=c(5,10,20,50,100), grid=TRUE, axis.title="infant mortality rate per 1000")

plot(box.cox(gdp, 0), box.cox(infant.mortality, 0))
box.cox.axis(0, side="above", 
  grid=TRUE, axis.title="GDP per capita")
box.cox.axis(0, side="right",
  grid=TRUE, axis.title="infant mortality rate per 1000")

qq.plot(logit(infant.mortality/1000))
prob.axis()

qq.plot(logit(infant.mortality/1000))
prob.axis(c(.005, .01, .02, .04, .08, .16))
[Package car version 1.1-0 Index]