Visualizing 2D smooth effects in 3D

This method plots an interactive 3D representation of a 2D smooth effect, using the rgl package.

# S3 method for mgcv.smooth.2D
plotRGL(
  x,
  se = TRUE,
  n = 40,
  residuals = FALSE,
  type = "auto",
  maxpo = 1000,
  too.far = 0,
  xlab = NULL,
  ylab = NULL,
  main = NULL,
  xlim = NULL,
  ylim = NULL,
  se.mult = 1,
  trans = identity,
  seWithMean = FALSE,
  unconditional = FALSE,
  ...
)

Arguments

x	a smooth effect object, extracted using mgcViz::sm.
se	when TRUE (default) upper and lower surfaces are added to the plot at se.mult (see below) standard deviations for the fitted surface.
n	sqrt of the number of grid points used to compute the effect plot.
residuals	if TRUE, then the partial residuals will be added.
type	the type of residuals that should be plotted. See residuals.gamViz.
maxpo	maximum number of residuals points that will be plotted. If number of datapoints > maxpo, then a subsample of maxpo points will be taken.
too.far	if greater than 0 then this is used to determine when a location is too far from data to be plotted. This is useful since smooths tend to go wild away from data. The data are scaled into the unit square before deciding what to exclude, and too.far is a distance within the unit square. Setting to zero can make plotting faster for large datasets, but care then needed with interpretation of plots.
xlab	if supplied then this will be used as the x label of the plot.
ylab	if supplied then this will be used as the y label of the plot.
main	used as title for the plot if supplied.
xlim	if supplied then this pair of numbers are used as the x limits for the plot.
ylim	if supplied then this pair of numbers are used as the y limits for the plot.
se.mult	a positive number which will be the multiplier of the standard errors when calculating standard error surfaces.
trans	monotonic function to apply to the smooth and residuals, before plotting. Monotonicity is not checked.
seWithMean	if TRUE the component smooths are shown with confidence intervals that include the uncertainty about the overall mean. If FALSE then the uncertainty relates purely to the centred smooth itself. Marra and Wood (2012) suggests that TRUE results in better coverage performance, and this is also suggested by simulation.
unconditional	if TRUE then the smoothing parameter uncertainty corrected covariance matrix is used to compute uncertainty bands, if available. Otherwise the bands treat the smoothing parameters as fixed.
...	currently unused.

Value

Returns NULL invisibly.

References

Marra, G and S.N. Wood (2012) Coverage Properties of Confidence Intervals for Generalized Additive Model Components. Scandinavian Journal of Statistics.

Examples

# Example 1: taken from ?mgcv::te, shows how tensor pruduct deals nicely with 
# badly scaled covariates (range of x 5% of range of z )
library(mgcViz)

# Simulate some data
test1 <- function(x,z,sx=0.3,sz=0.4) {
  x <- x*20
  (pi**sx*sz)*(1.2*exp(-(x-0.2)^2/sx^2-(z-0.3)^2/sz^2)+
                 0.8*exp(-(x-0.7)^2/sx^2-(z-0.8)^2/sz^2))
}
n <- 500
old.par <- par(mfrow=c(2,2))
x <- runif(n)/20;z <- runif(n);
xs <- seq(0,1,length=30)/20;zs <- seq(0,1,length=30)
pr <- data.frame(x=rep(xs,30),z=rep(zs,rep(30,30)))
truth <- matrix(test1(pr$x,pr$z),30,30)
f <- test1(x,z)
y <- f + rnorm(n)*0.2

# Fit with t.p.r.s. basis and plot
b1 <- gam(y~s(x,z))
plotRGL(sm(getViz(b1), 1))

rgl.close() # Close

# Fit with tensor products basis and plot (with residuals)
b2 <- gam(y~te(x,z))
plotRGL(sm(getViz(b2), 1), residuals = TRUE)

# We can still work on the plot, for instance change the aspect ratio
library(rgl)
aspect3d(1, 2, 1)

rgl.close() # Close