Model diagnostic plots

appraise(model, method = c("direct", "simulate", "normal"),
  n_uniform = 10, n_simulate = 50, type = c("deviance", "pearson",
  "response"), n_bins = c("sturges", "scott", "fd"), ncol = 2,
  level = 0.9, alpha = 0.2, ...)

Arguments

model

a fitted model. Currently only class "gam".

method

character; method used to generate theoretical quantiles.

n_uniform

numeric; number of times to randomize uniform quantiles in the direct computation method (method = "direct") for QQ plots.

n_simulate

numeric; number of data sets to simulate from the estimated model when using the simulation method (method = "simulate") for QQ plots.

type

character; type of residuals to use. Only "deviance", "response", and "pearson" residuals are allowed.

n_bins

character or numeric; either the number of bins or a string indicating how to calculate the number of bins.

ncol

numeric; number of columns to draw plots in. See cowplot::plot_grid().

level

numeric; the coverage level for QQ plot reference intervals. Must be strictly 0 < level < 1. Only used with method = "simulate".

alpha

numeric; the level of alpha transparency for the QQ plot reference interval when method = "simulate".

...

arguments passed to cowplot::plot_grid(), except for align and axis, which are set internally.

See also

Examples

library(mgcv)
#> Loading required package: nlme
#> This is mgcv 1.8-27. For overview type 'help("mgcv-package")'.
## simulate some data... dat <- gamSim(1, n = 400, dist = "normal", scale = 2)
#> Gu & Wahba 4 term additive model
mod <- gam(y ~ s(x0) + s(x1) + s(x2) + s(x3), data = dat) ## run some basic model checks, including checking ## smoothing basis dimensions... appraise(mod)