Add Squared Residual Visualization to a Plot

gf_squaresid() is a fully supported alias of gf_square_resid(). The name honors Tyler Haslam, the Utah high school teacher whose efforts shaped the residual and squared-residual visualizations and who requested this function by that name.

Usage

gf_square_resid(
  object = NULL,
  gformula = NULL,
  data = NULL,
  ...,
  model,
  aspect = 4/6,
  alpha = 0.1,
  xlab,
  ylab,
  title,
  subtitle,
  caption,
  geom = coursekata::GeomSquareResid,
  stat = coursekata::StatResid,
  position = "identity",
  show.legend = NA,
  show.help = NULL,
  inherit = FALSE,
  environment = parent.frame()
)

gf_squaresid(
  object = NULL,
  gformula = NULL,
  data = NULL,
  ...,
  model,
  aspect = 4/6,
  alpha = 0.1,
  xlab,
  ylab,
  title,
  subtitle,
  caption,
  geom = coursekata::GeomSquareResid,
  stat = coursekata::StatResid,
  position = "identity",
  show.legend = NA,
  show.help = NULL,
  inherit = FALSE,
  environment = parent.frame()
)

Arguments

object

A ggformula plot object, typically created with gf_point().

gformula

Not used. gf_square_resid() measures a model, not an aesthetic formula; a model given positionally lands here and is moved to model.

data

Not used. The residuals are measured over the data the plot was built from. Anything supplied here is left for ggformula and ggplot2 to answer, exactly as it is for any other gf_ layer.

...

Additional arguments. Typically these are (a) ggplot2 aesthetics to be set with attribute = value, such as color or fill, (b) ggplot2 aesthetics to be mapped with attribute = ~ expression, or (c) attributes of the layer as a whole.

model

A model already fit by lm() or aov(). The plot supplies the observations; the model supplies what it predicted for each of them. May be given positionally or as model =.

aspect

The square's aspect ratio. Default is 4/6. Must be named.

alpha

The transparency of the square's fill. Default is 0.1. Must be named.

xlab, ylab, title, subtitle, caption

Labels for the plot.

geom, stat, position

Not set by the caller. A squared residual is drawn by its own geom and stat, and moved by the position the observations are already drawn with, so that a square stays on the point it belongs to.

show.legend

Whether this layer contributes to the legend.

show.help

Print the layer's own help instead of drawing.

inherit

Whether the layer inherits the plot's aesthetics. FALSE, where gf_resid() is TRUE: a square is a filled region drawn in the geom's own colors, so inheriting a plot's mapped color outlines every square in the color of the group it measures instead of leaving one neutral area per observation. The axes and the prediction are stated outright, so nothing the square needs is lost by not inheriting. Set it to TRUE to take the outline anyway.

environment

The environment mappings are resolved in.

Value

A ggplot object with squared residual polygons added.

Details

Draws squared residual polygons between observed points and the values a fitted model predicts for them, so squared error is an area you can see. The square is built on the residual itself and turns with it: a model of the variable the plot puts on x squares the horizontal distance. Its side is scaled to stay square on the page rather than in data units.

Examples

# squared residuals can be drawn on a full data set, but with hundreds of
# points the plot gets hard to read
flipper_model <- lm(body_mass_kg ~ flipper_length_m, data = penguins)
gf_point(body_mass_kg ~ flipper_length_m, data = penguins) %>%
  gf_model(flipper_model) %>%
  gf_square_resid(flipper_model)


# a small sample makes the squared residuals much easier to see
set.seed(1)
penguins_20 <- sample(penguins, 20)

# squared residuals from the empty model (in blue)
empty_model <- lm(body_mass_kg ~ NULL, data = penguins_20)
gf_point(body_mass_kg ~ flipper_length_m, data = penguins_20) %>%
  gf_model(empty_model) %>%
  gf_square_resid(empty_model, color = "blue")


# squared residuals from a two-group model on a jitter plot (in firebrick)
gentoo_model <- lm(body_mass_kg ~ gentoo, data = penguins_20)
gf_jitter(body_mass_kg ~ gentoo, data = penguins_20, width = .1) %>%
  gf_model(gentoo_model) %>%
  gf_square_resid(gentoo_model, color = "firebrick")


# squared residuals from a regression model (in firebrick)
sample_flipper_model <- lm(body_mass_kg ~ flipper_length_m, data = penguins_20)
gf_point(body_mass_kg ~ flipper_length_m, data = penguins_20) %>%
  gf_model(sample_flipper_model) %>%
  gf_square_resid(sample_flipper_model, color = "firebrick")