robeth (version 2.7-6)

glmdev: The total deviance of the fitted generalizrd linear model

Description

Computes the sum of the vector deviance and other intermediate results

Usage

glmdev(y, ni, ci, wa, vtheta, offset = 0, icase = .dFvGet()$ics)

Value

A list with the following components:

dev

2*sum_i abs(Li-Ti)

thetas

The estimates of theta_i

li

The values of Li

sc

The alues of Ti

Arguments

y

The vector of observations

ni

The number of trial at xi in the binomial case (ics=2). Otherwise ni=1 for each xi.

ci

The constants ci

wa

The vector of ai=b/|Axi|

vtheta

The vector of xi^T

offset

Optional offset added to the linear predictor.

icase

Set ics=1 for Bernoulli case, ics=2 for Binomial case and ics=3 for Poisson case

References

Kuensch, H.R., Stefanski L.A., Carroll R.J. (1989). Conditionally unbiased bounded-influence estimation in general regression models, with application to generalized linear models. Journal of the American Statistical Association, 84, 460-466.

Marazzi, A. (1993). Algorithms, Routines, and S-functions for robust Statistics. Chapman and Hall, New York.

Marazzi A. (1997). Object oriented S-plus functions for robust discrete generalized linear models available in the doc folder of this package.