Plotting factor or logical parametric effects
These are the plotting methods for parametric factor or logical effects.
## S3 method for class 'multi.ptermFactor' plot(x, a.facet = list(), asFact = TRUE, ...) ## S3 method for class 'multi.ptermLogical' plot(x, ...) ## S3 method for class 'ptermFactor' plot(x, maxpo = 10000, trans = identity, ...) ## S3 method for class 'ptermLogical' plot(x, maxpo = 10000, trans = identity, ...)
x |
a factor or logical parametric effect object, extracted using mgcViz::pterm. |
a.facet |
arguments to be passed to ggplot2::facet_wrap or ggplot2::facet_grid. The former gets
called when |
asFact |
relevant only when working with models fitted with mqgamV. If
|
... |
currently unused. |
maxpo |
maximum number of residuals points that will be used by layers such as
|
trans |
monotonic function to apply to the fit, confidence intervals and residuals, before plotting. Monotonicity is not checked. |
An object of class plotSmooth.
# Simulate data and fit GAM
set.seed(3)
dat <- gamSim(1,n=2000,dist="normal",scale=20)
dat$fac <- as.factor( sample(c("A1", "A2", "A3"), nrow(dat), replace = TRUE) )
dat$logi <- as.logical( sample(c(TRUE, FALSE), nrow(dat), replace = TRUE) )
bs <- "cr"; k <- 12
b <- gam(y~fac + s(x0) + s(x1) + s(x2) + s(x3) + logi, data=dat)
o <- getViz(b, nsim = 0)
# Extract factor terms and plot it
pt <- pterm(o, 1)
plot(pt) + l_ciBar() + l_fitPoints(colour = 2) + l_rug(alpha = 0.2)
# Use barplot instead of points
pt <- pterm(o, 1)
plot(pt) + l_fitBar() + l_ciBar()
# Same with binary varible
pt <- pterm(o, 2)
plot(pt) + l_fitPoints() + l_ciBar()Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.