CookDco: Compute a cutoff value for Cook's D values

In sjpierce/piercer: Functions for Research and Statistical Computing

Compute a cutoff value for Cook's D values

Description

This function computes a cutoff for Cook's D values from a glm() model fit.

Usage

CookDco(x)

Arguments

x	A glm() model fit object.

Details

=============================================================================

Fox (1997, p. 281) suggested a cutoff value for identifying observations with high Cook's D values in a GLM model. This function computes that cutoff. Examining observations with Cook's D values larger than the cutoff may be warranted.

Value

A numeric value for the cutoff.

References

Fox, J. (1997). Applied regression analysis, linear models, and related methods. Thousand Oaks, CA: Sage Publications.

Examples

 m1 <- glm(formula = vs ~ wt + disp, family = binomial, data = mtcars)
 CookDco(m1)

sjpierce/piercer documentation built on Dec. 30, 2024, 3:28 p.m.