plotvgam {VGAM} | R Documentation |
Component functions of a vgam-class
object can be plotted
with plotvgam()
. These are on the scale of the linear/additive
predictor.
plotvgam(x, newdata = NULL, y = NULL, residuals = NULL, rugplot = TRUE, se = FALSE, scale = 0, raw = TRUE, offset.arg = 0, deriv.arg = 0, overlay = FALSE, type.residuals = c("deviance","working","pearson","response"), plot.arg = TRUE, which.term = NULL, which.cf = NULL, control = plotvgam.control(...), varxij = 1, ...)
In the following, M is the number of linear/additive predictors, and r is the number of columns of the constraint matrix of interest.
x |
A fitted VGAM object, e.g., produced by
vgam() , vglm() , or rrvglm() . |
newdata |
Data frame. May be used to reconstruct the original data set. |
y |
Unused. |
residuals |
Logical. If TRUE then residuals are plotted.
See type.residuals |
rugplot |
Logical. If TRUE then a rug plot is plotted at the
foot of each plot. These values are jittered to expose ties.
|
se |
Logical. If TRUE then approximate +-2 pointwise
standard error bands are included in the plot.
|
scale |
Numerical. By default, each plot will have its own
y-axis scale. However, by specifying a value, each plot's y-axis
scale will be at least scale wide.
|
raw |
Logical. If TRUE then the smooth functions are those
obtained directly by the algorithm, and are plotted without
having to premultiply with the constraint matrices.
If FALSE then the smooth functions have been premultiply by
the constraint matrices.
The raw argument is directly fed into predict.vgam() .
|
offset.arg |
Numerical vector of length r.
These are added to the component functions. Useful for
separating out the functions when overlay is TRUE .
If overlay is TRUE and there is one covariate then
using the intercept values as the offsets can be a good idea.
|
deriv.arg |
Numerical. The order of the derivative.
Should be assigned an small
integer such as 0, 1, 2. Only applying to s() terms,
it plots the derivative.
|
overlay |
Logical. If TRUE then component functions of the same
covariate are overlaid on each other.
The functions are centered, so offset.arg can be useful
when overlay is TRUE .
|
type.residuals |
if residuals is TRUE then the first
possible value
of this vector, is used to specify the type of
residual. |
plot.arg |
Logical. If FALSE then no plot is produced. |
which.term |
Character or integer vector containing all
terms to be
plotted, e.g., which.term=c("s(age)", "s(height")) or
which.term=c(2,5,9) .
By default, all are plotted. |
which.cf |
An integer-valued vector specifying which linear/additive predictors are to be plotted. The values must be from the set {1,2,...,r}. By default, all are plotted. |
control |
Other control parameters. See
plotvgam.control . |
... |
Other arguments that can be fed into
plotvgam.control . This includes line colors,
line widths, line types, etc.
|
varxij |
Positive integer.
Used if xij of vglm.control was used,
this chooses which inner argument the component is plotted against.
This argument is related to raw=TRUE and terms such as
NS(dum1,dum2) and constraint matrices that have more than
one column. The default would plot the smooth against dum1
but setting varxij=2 could mean plotting the smooth against
dum2 .
See the VGAM website for further information.
|
Many of plotvgam()
's options can be found in
plotvgam.control
, e.g., line types, line widths,
colors.
The original object, but with the preplot
slot of the object
assigned information regarding the plot.
While plot(fit)
will work if class(fit)
is "vgam"
, it is necessary to use plotvgam(fit)
explicitly otherwise.
plotvgam()
is quite buggy at the moment.
Thomas W. Yee
Yee, T. W. and Wild, C. J. (1996) Vector generalized additive models. Journal of the Royal Statistical Society, Series B, Methodological, 58, 481–493.
Documentation accompanying the VGAM package at http://www.stat.auckland.ac.nz/~yee contains further information and examples.
vgam
,
plotvgam.control
,
predict.vgam
,
vglm
.
coalminers = transform(coalminers, Age = (age - 42) / 5) fit = vgam(cbind(nBnW,nBW,BnW,BW) ~ s(Age), binom2.or(zero=NULL), coalminers) ## Not run: par(mfrow=c(1,3)) plot(fit, se=TRUE, ylim=c(-3,2), las=1) plot(fit, se=TRUE, which.cf=1:2, lcol="blue", scol="red", ylim=c(-3,2)) plot(fit, se=TRUE, which.cf=1:2, lcol="blue", scol="red", overlay=TRUE) ## End(Not run)