Plot 1D smooth effects for gam models — plot

Plots 1D smooth effects for a GAM model fitted with gam or bam.

Usage

plot_1Dsmooth(
  model,
  plot_ci = TRUE,
  select,
  alpha = 0.05,
  ylim = NULL,
  method_expTransform = "simple",
  return_plotData = FALSE
)

Arguments

model: GAM model fitted with gam or bam.
plot_ci: If TRUE CIs are plotted. Only used if plot_type = 1.
select: Index of smooth term to be plotted.
alpha: (1-alpha) CIs are calculated. The default 0.05 leads to 95% CIs.
ylim: Optional limits of the y-axis.
method_expTransform: One of c("simple","delta"), stating if standard errors and confidence interval limits should be transformed by a simple exp transformation or using the delta method. The delta method can be unstable in situations and lead to negative confidence interval limits. Only used when the model was estimated with a log or logit link.
return_plotData: If TRUE, the dataset prepared for plotting is returned. Defaults to FALSE.

Value

ggplot object

Details

If the model was estimated with a log or logit link, the function automatically performs an exponential transformation of the effect, see argument method_expTransform.

Author

Alexander Bauer alexander.bauer@stat.uni-muenchen.de

Examples

library(APCtools)
library(mgcv)

data(travel)
model <- gam(mainTrip_distance ~ te(age, period) + residence_region +
             household_size + s(household_income), data = travel)

plot_1Dsmooth(model, select = 2)