InfCases: Identify influential cases (high leverage and high Cook's D)

In sjpierce/piercer: Functions for Research and Statistical Computing

Identify influential cases (high leverage and high Cook's D)

Description

This function identifies influential cases from a glm() model by finding those that exceed cutoffs for high leverage and high Cook's D.

Usage

InfCases(x, digits = 3)

Arguments

x	A glm() model fit object.
digits	An integer specifying the number of decimal places to used when rounding the result. Defaults to 3.

Details

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

Fox (1997, p. 280-281) suggested cutoff values for identifying observations with high leverage hat values and high Cook's D values in a GLM model. Listing these influential observations is a quick way to inspect a model fit.

Value

A data frame showing observations that have both high leverage and high Cook's D.

References

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

See Also

hatco for leverage cutoff, CookDco for Cook's D cutoff.

Examples

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

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