daniel.paper | R Documentation |
The daniel.paper
function draws a graph-paper grid suitable for manually constructing a half-normal plot of effects. The paper is customized to the number of effects to be plotted, thus making the task as simple as possible.
daniel.paper(n.effects = 15, linear = 0:40, a = 0.375, rank.axis = c("y", "x"), type = c("half.normal", "normal"), theme = "blue", lin.lab, rank.lab)
n.effects |
Numeric vector of effects or contrasts to be explored. |
linear |
sequence of numbers to use for the linear scale. |
a |
The adjustment used in scaling and centering ranks in the interval (0, 1). The ith ordered (half-) normal score is computed as the (i - a) / (n + 1 - 2*a) quantile of the reference distribution. The value should always be less than 1, and is recommended to be in [0,.5]. The scale becomes somewhat more nonlinear as a increases. |
rank.axis |
Character value of |
type |
Character value matching |
theme |
Character giving the name of the theme to use for the grid lines. The default of |
lin.lab, rank.lab |
Labels for the linear and rank scales. |
Use of type = "normal"
is discouraged, as is discussed in the Details section in hnplot
.
A custom theme, say "foo"
, may be created by creating a list
named foo_thm
, which should contain two elements named major
and minor
, and (optionally) axis
. major
must be a named list
with graphical parameters col
, lty
, and lwd
as described in par
. minor
only requires col
and lty
, as minor lines are always drawn using lwd = 1
. axis
must contain col
and lwd
, which are used for the tick marks and labels on the rank scale. If axis
is not included, major
is used.
Nothing is returned.
Russell V. Lenth
Daniel, C (1959) Use of Half-Normal Plots in Interpreting Factorial Two-Level Experiments. Technometrics, 1(4), 311-341
hnplot
require("unrepx") old.par <- par(mar = c(5, 5, 1, 1) + .1) daniel.paper(15) neon_thm <- list( major = list(col = "green", lty = 1, lwd = 2), minor = list(col = "orange", lty = 1), axis = list(col = "magenta", lwd = 2) ) daniel.paper(31, rank.axis = "x", theme = "neon") par(old.par)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.