cubinf.summaries: Functions required by the corresponding access functions

In robcbi: Conditionally Unbiased Bounded Influence Estimates

Functions required by the corresponding access functions

Description

Auxiliary functions for residuals(), summary(), covar(), deviance(), family(), Rank(), rscale(), weights().

Usage

## S3 method for class 'cubinf'
residuals(object, type = c("deviance", "pearson", "response"), ...)

## S3 method for class 'cubinf'
summary(object, ...)
 
## S3 method for class 'cubinf'
covar(object)
 
## S3 method for class 'cubinf'
deviance(object, ...)

## S3 method for class 'cubinf'
family(object, ...)
 
## S3 method for class 'cubinf'
Rank(object)
 
## S3 method for class 'cubinf'
rscale(object)
 
## S3 method for class 'cubinf'
weights(object)

Arguments

object	An object inheriting from class "cubinf".
type	A character string for the residual type.
...	Optional arguments. For summary, it can be correlation=TRUE.

Details

The generic functions coef, residuals, fitted, formula, deviance, rscale, r.squared, covar, correl, weights and Rank can be used to extract elements from an object of class "cubinf" returned by glm. The class "lm" functions effects, alias, add1, drop1, codekappa, proj, step, influence, anova and sensitivity are not implemented to objects of class "cubinf".

Value

summary.cubinf returns a list with the following components:

call	The model formula used in glm.
terms	Terms object used in fitting the model.
coefficients	A matrix with three columns, containing the coefficients, their standard errors and the corresponding t-statistics.
dispersion	Dispersion coefficient
df	Degrees of freedom for model and residuals.
deviance.resid	Deviance residuals
family	The family function used: binomial or poisson
cov.unscaled	Unscaled covariance matrix of coefficient estimates.
correlation	Correlation matrix of coefficient estimates.
deviance	Deviance.
null.deviance	Null deviance.
iter	Number of iterations of the main algorithm.
nas	A logical vector whose i-th component is TRUE if the i-th coefficient is NA.

See Also

The model fitting function glm, cubinf

Examples

 library(robcbi)
 data(Finney)
 Vol <- Finney$Vol; Rate <- Finney$Rate; Resp <- Finney$Resp
 lVol <-log(Vol); lRate <- log(Rate)
 z.glm <- glm(Resp~lVol+lRate,family=binomial)
 summary(z.glm)
 z.cub <- glm(Resp~lVol+lRate,family=binomial,method="cubinf", ufact=3.2)
 summary(z.cub)
 weights(z.cub)
 covar(z.cub)
 deviance(z.cub)
 Rank(z.cub)
 residuals(z.cub)
 rscale(z.cub)

robcbi documentation built on Aug. 22, 2023, 1:06 a.m.