Methods for zeroinfl Objects

Methods for extracting information from fitted zero-inflated regression model objects of class "zeroinfl".

Usage

# S3 method for class 'zeroinfl'
predict(object, newdata,
  type = c("response", "prob", "count", "zero"), na.action = na.pass,
  at = NULL, ...)
# S3 method for class 'zeroinfl'
residuals(object, type = c("pearson", "response"), ...)

# S3 method for class 'zeroinfl'
coef(object, model = c("full", "count", "zero"), ...)
# S3 method for class 'zeroinfl'
vcov(object, model = c("full", "count", "zero"), ...)

# S3 method for class 'zeroinfl'
terms(x, model = c("count", "zero"), ...)
# S3 method for class 'zeroinfl'
model.matrix(object, model = c("count", "zero"), ...)

Arguments

object, x

an object of class "zeroinfl" as returned by zeroinfl.

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.

at

optionally, if type = "prob", a numeric vector at which the probabilities are evaluated. By default 0:max(y) is used where y is the original observed response.

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 "zeroinfl", 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 (estimated from the Hessian in the numerical optimization of the log-likelihood). As usual, the summary method returns an object of class "summary.zeroinfl" 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 components 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), the predicted mean from the count component (without zero inflation) and the predicted probability for the zero component. The residuals method can compute raw residuals (observed - fitted) and Pearson residuals (raw residuals scaled by square root of variance function).

The terms and model.matrix extractors can be used to extract the relevant information for either component of the model.

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

Author

Achim Zeileis <Achim.Zeileis@R-project.org>

See also

zeroinfl

Examples

data("bioChemists", package = "ModTools")

fm_zip <- zeroinfl(art ~ ., data = bioChemists)
plot(residuals(fm_zip) ~ fitted(fm_zip))


coef(fm_zip)
#> count_(Intercept)    count_femWomen  count_marMarried        count_kid5 
#>       0.640838981      -0.209144354       0.103750213      -0.143320239 
#>         count_phd        count_ment  zero_(Intercept)     zero_femWomen 
#>      -0.006166143       0.018097723      -0.577060250       0.109751512 
#>   zero_marMarried         zero_kid5          zero_phd         zero_ment 
#>      -0.354017556       0.217095103       0.001274820      -0.134114310 
coef(fm_zip, model = "count")
#>  (Intercept)     femWomen   marMarried         kid5          phd         ment 
#>  0.640838981 -0.209144354  0.103750213 -0.143320239 -0.006166143  0.018097723 

summary(fm_zip)
#> 
#> Call:
#> zeroinfl(formula = art ~ ., data = bioChemists)
#> 
#> Pearson residuals:
#>     Min      1Q  Median      3Q     Max 
#> -2.3253 -0.8652 -0.2826  0.5404  7.2976 
#> 
#> Count model coefficients (poisson with log link):
#>              Estimate Std. Error z value Pr(>|z|)    
#> (Intercept)  0.640839   0.121307   5.283 1.27e-07 ***
#> femWomen    -0.209144   0.063405  -3.299 0.000972 ***
#> marMarried   0.103750   0.071111   1.459 0.144567    
#> kid5        -0.143320   0.047429  -3.022 0.002513 ** 
#> phd         -0.006166   0.031008  -0.199 0.842376    
#> ment         0.018098   0.002294   7.888 3.07e-15 ***
#> 
#> Zero-inflation model coefficients (binomial with logit link):
#>              Estimate Std. Error z value Pr(>|z|)   
#> (Intercept) -0.577060   0.509386  -1.133  0.25728   
#> femWomen     0.109752   0.280082   0.392  0.69517   
#> marMarried  -0.354018   0.317611  -1.115  0.26501   
#> kid5         0.217095   0.196483   1.105  0.26920   
#> phd          0.001275   0.145263   0.009  0.99300   
#> ment        -0.134114   0.045243  -2.964  0.00303 **
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 
#> 
#> Number of iterations in BFGS optimization: 19 
#> Log-likelihood: -1605 on 12 Df
logLik(fm_zip)
#> 'log Lik.' -1604.773 (df=12)