surveillance (version 1.4-2)

twinstim_iafplot: Plot the spatial or temporal interaction function of a twimstim

Description

The function plots the fitted temporal or (isotropic) spatial interaction function of a twinstim object.

Usage

iafplot(object, which = c("siaf", "tiaf"),
    types = 1:nrow(object$qmatrix),
    conf.type = if (length(pars) > 1) "bootstrap" else "parbounds",
    conf.level = 0.95, conf.B = 999,
    ngrid = 101, col.estimate = rainbow(length(types)), col.conf = col.estimate,
    alpha.B = 0.15, lwd = c(3,1), lty = c(1,2), xlim = c(0,eps), ylim = c(0,1),
    add = FALSE, xlab = NULL, ylab = NULL, ...)

Arguments

object

Object of class "twinstim" containing the fitted model.

which

Argument indicating which of the two interaction functions to plot. Possible values are "siaf" (default) for the spatial interaction function and "tiaf" for the temporal interaction function.

types

In case of a marked twinstim, for which event types should the interaction function be plotted.

conf.type

type of confidence interval to produce. If "bootstrap", conf.B parameter values (vectors) are sampled from the asymptotic (multivariate) normal distribution of the ML estimate(s) of the interaction function parameters

conf.level

the confidence level required. For conf.type = "bootstrap" it may also be specified as NA, in which case all conf.B bootstrapped functions will be plotted with transparency value given by alpha.B

conf.B

number of samples for the "bootstrap" confidence interval.

ngrid

number of evaluation points of the interaction function in the interval c(0,xlim[2]).

col.estimate

vector of colours to use for the function point estimates of the different types.

col.conf

vector of colours to use for the confidence intervals of the different types.

alpha.B

alpha transparency value (as relative opacity) used for the conf.B bootstrapped interaction functions in case conf.level = NA

lwd, lty

Numeric vectors of length two specifying the line width and type of point estimates (first element) and confidence limits (second element), respectively.

xlim, ylim

Vectors of length two containing the x- and y-axis limit of the plot. The default y-axis ranges from 0 to 1. The default x-axis ranges from 0 to the length of the observation period (which="tiaf") or the length of the diagonal

add

Add to an existing plot?

xlab, ylab

labels for the axes with NULL providing sensible defaults.

...

Additional arguments passed to the default plot method.

Value

• A plot is created -- see e.g. Figure 3(b) in Meyer et al. (2012). NULL is returned (invisibly).

encoding

latin1

References

Meyer, S., Elias, J. and H�{oe}hle, M. (2012): A space-time conditional intensity model for invasive meningococcal disease occurrence. Biometrics, 68, 607-616. DOI-Link: http://dx.doi.org/10.1111/j.1541-0420.2011.01684.x

See Also

plot.twinstim, which calls this function.

Examples

data(imdepifit)
iafplot(imdepifit, "tiaf", types=1)   # tiaf.constant(), not very exciting
iafplot(imdepifit, "siaf", xlim=c(0,200), types=1,   # same for types=2
     col.estimate=1, lwd=c(2,1))
# alternative: bootstrap-CI (actually only useful if iaf$npars > 1)
iafplot(imdepifit, "siaf", add=TRUE, types=1, col.estimate=0, ngrid=500,
     conf.type="bootstrap", col.conf=2)

## FIXME: fit model with 2-parameter Lomax kernel as siaf (this takes a
##        while and does not converge properly...)
#data(imdepi)
#imdepifit_lomax <- update(imdepifit,
#    siaf = siaf.lomax(1),
#    optim.args = list(par=c(coef(imdepifit), 0), control=list(REPORT=1)),
#    nCub = 3, nCub.adaptive = FALSE, model = FALSE, cumCIF = FALSE
#)