predict.nbreg: Methods for nbreg Objects

In countreg: Count Data Regression

Methods for nbreg Objects

Description

Methods for extracting information from fitted negative binomial count regression model objects of class "nbreg".

Usage

## S3 method for class 'nbreg'
predict(object, newdata,
  type = c("response", "prob", "theta", "parameters"), na.action = na.pass, ...)
## S3 method for class 'nbreg'
residuals(object, type = c("pearson", "deviance", "response"), ...)

## S3 method for class 'nbreg'
coef(object, model = c("full", "mu", "theta"), ...)
## S3 method for class 'nbreg'
vcov(object, model = c("full", "mu", "theta"), ...)

## S3 method for class 'nbreg'
terms(x, model = c("full", "mu", "theta"), ...)
## S3 method for class 'nbreg'
model.matrix(object, model = c("mu", "theta"), ...)

Arguments

object, x	an object of class "nbreg" as returned by nbreg.
newdata	optionally, a data frame in which to look for variables with which to predict. If omitted, the original observations are used.
type	character specifying the type of predictions or residuals, respectively. For details see below.
na.action	function determining what should be done with missing values in newdata. The default is to predict NA.
model	character specifying for which component of the model the terms or model matrix should be extracted.
...	currently not used.

Details

A set of standard extractor functions for fitted model objects is available for objects of class "nbreg", including methods to the generic functions print and summary which print the estimated coefficients along with some further information. The summary in particular supplies partial Wald tests based on the coefficients and the covariance matrix. As usual, the summary method returns an object of class "summary.nbreg" containing the relevant summary statistics which can subsequently be printed using the associated print method.

The methods for coef and vcov by default return a single vector of coefficients and their associated covariance matrix, respectively, i.e., all coefficients are concatenated. By setting the model argument, the estimates for the corresponding model component can be extracted.

Both the fitted and predict methods can compute fitted responses. The latter additionally provides the predicted density (i.e., probabilities for the observed counts) and the predicted dispersion parameter theta. The residuals method can compute raw residuals (observed - fitted), Pearson residuals (raw residuals scaled by square root of variance function), and deviance residuals. The latter are only supported for negative binomial type 2 models (dist = NB2) (includes NBH).

A logLik method is provided, hence AIC can be called to compute information criteria.

See Also

nbreg

Examples

data("CrabSatellites", package = "countreg")
fm <- nbreg(satellites ~ width + color, data = CrabSatellites)

plot(residuals(fm, type = "pearson") ~ fitted(fm))

coef(fm)
summary(fm)
logLik(fm)
AIC(fm)

countreg documentation built on Dec. 4, 2023, 3:09 a.m.