Regression Diagnostics for Generalized Linear Models

Provides regression diagnostics for a generalized linear model fit with glm or regress. Currently, binary logistic regression models are supported.

# S3 method for glm
diagnostics(x, alpha = 0.4, span = 0.8, plot = TRUE, ...)

Arguments

x: an object of class c("glm")
alpha: numeric; transparency for plot points (default=0.4)
span: numeric; smoothing parameter for loess fit lines (default=0.8)
plot: logical; If TRUE (the default), graphs are printed. Otherwise, they are returned invisibly.
...: not currently used

Value

A three component list containing ggplot2 graphs: crplots, vifplot, and influenceplot.

Details

The diagnostics function is a wrapper for several diagnostic plotting functions:

Linearity: Linearity of the explanatory-response relationships are assessed via Component + Residual (partial residual) plots (cr_plots). If there is a single predictor, a scatter plot with linear and loess lines is produced.
Multicollinearity: Multicollinearity is assessed via variance inflation factors (vif_plot). If there is a single predictor variable, this section is skipped.
Outliers, leverage, and influence: A influence plot identifies outliers and influential observations (influence_plot).

Note

Each function relies heavily on the car package. See the help for individual functions for details.

Examples

fit <- glm(caesarian ~ age + bp + delivery.time, family = binomial, data = caesarian)
diagnostics(fit)