fortify.lm: Supplement the data fitted to a linear model with model fit...

In tidyverse/ggplot2: Create Elegant Data Visualisations Using the Grammar of Graphics

Supplement the data fitted to a linear model with model fit statistics.

Description

This method is deprecated because using broom::augment() is a better solution to supplement data from a linear model. If you have missing values in your model data, you may need to refit the model with na.action = na.exclude.

Usage

## S3 method for class 'lm'
fortify(model, data = model$model, ...)

Arguments

model	linear model
data	data set, defaults to data used to fit model
...	not used by this method

Value

The original data with extra columns:

.hat	Diagonal of the hat matrix
.sigma	Estimate of residual standard deviation when corresponding observation is dropped from model
.cooksd	Cooks distance, cooks.distance()
.fitted	Fitted values of model
.resid	Residuals
.stdresid	Standardised residuals

Examples

mod <- lm(mpg ~ wt, data = mtcars)

# Show augmented model
head(augment(mod))
head(fortify(mod))

# Using augment to convert model to ready-to-plot data
ggplot(augment(mod), aes(.fitted, .resid)) +
  geom_point() +
  geom_hline(yintercept = 0) +
  geom_smooth(se = FALSE)

# Colouring by original data not included in the model
ggplot(augment(mod, mtcars), aes(.fitted, .std.resid, colour = factor(cyl))) +
  geom_point()

tidyverse/ggplot2 documentation built on Jan. 29, 2025, 6:53 a.m.