spread_plot: Spread-Level Plot

In Rkabacoff/qacReg: Multiple Regression and Logistic Regression

Spread-Level Plot

Description

Creates a plot for examining the possible dependence of spread on level using the studentized residuals from a linear model.

Usage

spread_plot(x, alpha = 0.4, n.labels = 0, span = 0.75)

Arguments

x	an object of class "lm".
alpha	numeric; degree of transparency for points (0 to 1, default=0.4).
n.labels	integer; the number of largest residuals to label (default=0).
span	numeric; smoothing parameter for loess fit line (default=0.75)

Details

This function is a modification of the spreadLevelPlot function in the car package, using ggplot2 rather than base graphics.

Value

a ggplot2 graph

Note

The graph plots the fitted values against the absolute studentized residuals on logarithmic scales. A robust linear fit line and a loess fit line are also plotted.

See Also

spreadLevelPlot, rlm

Examples

mtcars$am <- factor(mtcars$am)
fit <- lm(mpg ~ wt + am + disp + hp, mtcars)
spread_plot(fit)

Rkabacoff/qacReg documentation built on Aug. 1, 2022, 11:11 p.m.