Besides print and summary methods there are also some standard extraction methods defined for objects of class "hhh4" resulting from a call to hhh4. The implementation is illustrated in Meyer et al. (2017, Section 5), see vignette("hhh4_spacetime").

# S3 method for hhh4
print(x, digits = max(3, getOption("digits") - 3), ...)
# S3 method for hhh4
summary(object, maxEV = FALSE, ...)

# S3 method for hhh4
coef(object, se = FALSE, reparamPsi = TRUE, 
     idx2Exp = NULL, amplitudeShift = FALSE, ...)
# S3 method for hhh4
fixef(object, ...)
# S3 method for hhh4
ranef(object, tomatrix = FALSE, intercept = FALSE, ...)
# S3 method for hhh4
coeflist(x, ...)

# S3 method for hhh4
formula(x, ...)
# S3 method for hhh4
nobs(object, ...)
# S3 method for hhh4
logLik(object, ...)

# S3 method for hhh4
vcov(object, reparamPsi = TRUE, 
     idx2Exp = NULL, amplitudeShift = FALSE, ...)
# S3 method for hhh4
confint(object, parm, level = 0.95, 
        reparamPsi = TRUE, idx2Exp = NULL, amplitudeShift = FALSE, ...)

# S3 method for hhh4
residuals(object, type = c("deviance", "response"), ...)


x, object

an object of class "hhh4".


the number of significant digits to use when printing


logical indicating if the summary should contain the (range of the) dominant eigenvalue as a measure of the importance of the epidemic components. By default, the value is not calculated as this may take some seconds depending on the number of time points and units in object$stsObj.


For the print, summary, fixef, ranef, and coeflist methods: arguments passed to coef.
For the remaining methods: unused (argument of the generic).


logical. If TRUE (default), the overdispersion parameter from the negative binomial distribution is transformed from internal scale (-log) to standard scale, where zero corresponds to a Poisson distribution.


logical switch indicating if standard errors are required


integer vector selecting the parameters which should be returned on exp-scale. Alternatively, idx2Exp = TRUE will exp-transform all parameters except for those associated with log() covariates or already affected by reparamPsi or amplitudeShift.


logical switch indicating whether the parameters for sine/cosine terms modelling seasonal patterns (see addSeason2formula) should be transformed to an amplitude/shift formulation.


logical. If FALSE (default), the vector of all random effects is returned (as used internally). However, for random intercepts of type="car", the number of parameters is one less than the number of regions and the individual parameters are not obviously linked to specific regions. Setting tomatrix to TRUE returns a more useful representation of random effects in a matrix with as many rows as there are regions and as many columns as there are random effects. Here, any CAR-effects are transformed to region-specific effects.


logical. If FALSE (default), the returned random effects represent zero-mean deviations around the corresponding global intercepts of the log-linear predictors. Setting intercept=TRUE adds these global intercepts to the result (and implies tomatrix=TRUE).


a vector of numbers or names, specifying which parameters are to be given confidence intervals. If missing, all parameters are considered.


the confidence level required.


the type of residuals which should be returned. The alternatives are "deviance" (default) and "response".


The coef-method returns all estimated (regression) parameters from a hhh4 model. If the model includes random effects, those can be extracted with ranef, whereas fixef returns the fixed parameters. The coeflist-method extracts the model coefficients in a list (by parameter group).

The formula-method returns the formulae used for the three log-linear predictors in a list with elements "ar", "ne", and "end". The nobs-method returns the number of observations used for model fitting. The logLik-method returns an object of class "logLik" with "df" and "nobs" attributes. For a random effects model, the value of the penalized log-likelihood at the MLE is returned, but degrees of freedom are not available (NA_real_). As a consequence, AIC and BIC are only well defined for models without random effects; otherwise these functions return NA_real_.

The vcov-method returns the estimated variance-covariance matrix of the regression parameters. The estimated variance-covariance matrix of random effects is available as object$Sigma. The confint-method returns Wald-type confidence intervals (assuming asymptotic normality).

The residuals-method extracts raw ("response") or scaled ("deviance") residuals from the model fit similar to residuals.glm for Poisson or NegBin GLM's.

See also

the plot and update methods for fitted "hhh4" models.


Michaela Paul and Sebastian Meyer


Meyer, S., Held, L. and Höhle, M. (2017): Spatio-temporal analysis of epidemic phenomena using the R package surveillance. Journal of Statistical Software, 77 (11), 1-55. doi: 10.18637/jss.v077.i11