| rootogram {vcd} | R Documentation |
Rootograms of observed and fitted values.
## Default S3 method:
rootogram(x, fitted, names = NULL, scale = c("sqrt", "raw"),
type = c("hanging", "standing", "deviation"),
rect_gp = gpar(fill = "lightgray"), lines_gp = gpar(col = "red"),
points_gp = gpar(col = "red"), pch = 19,
xlab = NULL, ylab = NULL, ylim = NULL,
name = "rootogram", newpage = TRUE, pop = TRUE, ...)
x |
either a vector or a 1-way table of frequencies. |
fitted |
a vector of fitted frequencies. |
names |
a vector of names passed to grid_barplot, if set
to NULL the names of x are used. |
scale |
a character string indicating whether the values should be plotted on the raw or square root scale. |
type |
a character string indicating if the bars for the observed frequencies should be hanging or standing or indicate the deviation between observed and fitted frequencies. |
rect_gp |
a "gpar" object controlling the grid graphical
parameters of the rectangles. |
lines_gp |
a "gpar" object controlling the grid graphical
parameters of the lines. |
points_gp |
a "gpar" object controlling the grid graphical
parameters of the points. |
pch |
plotting character for the points. |
xlab |
a label for the x axis. |
ylab |
a label for the y axis. |
ylim |
limits for the y axis. |
name |
name of the plotting viewport. |
newpage |
logical. Should grid.newpage be called
before plotting? |
pop |
logical. Should the viewport created be popped? |
... |
further arguments passed to grid_barplot. |
The observed frequencies are displayed as bars and the fitted frequencies as a line. By default a sqrt scale is used to make the smaller frequencies more visible.
Achim Zeileis Achim.Zeileis@R-project.org
J. W. Tukey (1977), Exploratory Data Analysis. Addison Wesley, Reading, MA.
M. Friendly (2000), Visualizing Categorical Data. SAS Institute, Cary, NC.
## Simulated data examples:
dummy <- rnbinom(200, size = 1.5, prob = 0.8)
observed <- table(dummy)
fitted1 <- dnbinom(as.numeric(names(observed)),
size = 1.5, prob = 0.8) * sum(observed)
fitted2 <- dnbinom(as.numeric(names(observed)),
size = 2, prob = 0.6) * sum(observed)
rootogram(observed, fitted1)
rootogram(observed, fitted2)
## Real data examples:
data("HorseKicks")
HK.fit <- goodfit(HorseKicks)
summary(HK.fit)
plot(HK.fit)
## or equivalently
rootogram(HK.fit)
data("Federalist")
F.fit <- goodfit(Federalist, type = "nbinomial")
summary(F.fit)
plot(F.fit)