dfCompile.Gam: Creates an augmented data frame for 'Gam' objects (for...
In benjaminleroy/ggDiagnose: Wrapper for Diagnostic Plots with ggplot2

Description Usage Arguments Details Value Examples

Though a similar idea to broom::augment this returns very different values.

1	dfCompile.Gam(x, residuals = NULL, terms = labels.Gam(x), ...)

`x`	`Gam` object from `gam` library
`residuals`	if TRUE, partial deviance residuals are plotted along with the fitted terms<e2><80><94>default is FALSE. If residuals is a vector with the same length as each fitted term in x, then these are taken to be the overall residuals to be used for constructing the partial residuals.
`terms`	subsets of the terms can be selected.
`...`	(extra parameters, passed to dfCompile.Gam).

original data frame: original data frame used to create lm or glm object
.resid: residuals between predicted verse actual y values

For each variable in the model we have the following variables:

.smooth._: part of the predicted value from variable _ for each observation
se.smooth._.lower: lower pointwise twice-standard-error values for each point relative to the part of the predicted value from variable _
se.smooth._.upper: the "upper" version of se.smooth._.lower

augmented data.frame, see details for more information

library(tidyverse)

gam.object <- gam::gam(Sepal.Length ~ gam::s(Sepal.Width) + Species,
                       data = iris)

dfCompile.Gam(gam.object) %>% head