leCessie.test: The le Cessie-van Houwelingen Test

View source: R/lecessie.R

leCessie.testR Documentation

The le Cessie-van Houwelingen Test

Description

Performs the le Cressie-van Houwelingen test for goodness-of-fit for a logistic regression model.

Usage

leCessie.test(object, bandwidth, newterms)

Arguments

object

an object of class "glm" on which to perform the test.

bandwidth

the bandwidth for smoothing the residuals.

newterms

any new variables to add to the model. Expressed as the right-hand side of a formula.

Details

If bandwidth is missing, then the mean distance between observations is used.

Value

An object of class "lecessie" having these components:

method

a description of the method.

statistic

the test statistic.

parameters

the degrees of freedom of the chi-squared test.

p.value

the attained p-level of the test statistic.

data.name

the name of object.

alternative

the alternate hypothesis–"some lack of fit."

estimate

the estimated values for the test.

object

the original object.

target.object

the object with any added newterms.

bandwidth

the bandwidth used for smoothing the residuals.

max.distance

the maximum distance between observations.

smoothed.residuals

the smoothed residuals.

distance.matrix

a matrix of the distances between observations.

hat

the hat matrix.

Note

The null hypothesis is "no lack of fit." Rejection of the null hypothesis indicates "some lack of fit."

References

le Cessie, S. and van Houwelingen, H.C., 1995, Testing the fit of a regression model via score tests in random effects models: Biometrics, v. 51, p 600-614.

See Also

binaryReg


USGS-R/smwrStats documentation built on Oct. 11, 2022, 6:15 a.m.