stukel: Stukels test of the logistic link

In logisticDx: Diagnostic tests for logistic regression models

Description

Calculates Stukels test for a logistic regression model.

This determines the appropriateness of the logistic link.

Two new covariates, z1 and z2 are generated such that

z1=0.5*logit^2*I(pi>=0.5), z2=-0.5*logit^2*I(pi<=0.5)

where I(arg)=1 where arg is true and =0 where false.

Tests if significant change occurs in the model with the addition of these coefficients.

Usage

  stukel(object,
    alternative = c("both", "alpha1", "alpha2"))

Arguments

object	An object of class glm
alternative	add both z1 and z2 to model or just one of the above

Value

A list with the following elemens:

statistic	value of statistic
parameter	degrees of freedom
p.value	if <0.05 suggests should accept null hypothesis that logistic model is incorrect for the data
alternative	alternative
method	method
data.name	name of object
allstat	statistics for all tests
allpar	degrees of freedom
allpval	all p values

Author(s)

Brett Presnell

References

University of Florida

Examples

set.seed(1)
m1 <- genLogiDf(b=3,f=0,c=0,n=50)$model
stukel(m1)

logisticDx documentation built on May 2, 2019, 6:30 p.m.