These functions are internally used helper function for cniperCont
and cniperPointPlot
.
.plotData(data, dots, fun, L2Fam, IC, jit.fac, jit.tol, plotInfo )
.getFunCnip(IC1,IC2, risk, L2Fam, r, b20=NULL)
If argument dots
contains an element return.Order
and
if this equals TRUE
, the order of the (remaining) observations
given by their original index is returned (remaining means: after a possible
reduction by argument which.lbs
, and ordering is according fun
;
otherwise we return invisible()
as usual.
a vectorized function to compute the risk difference.
data to be plot in
list; argument ...
from the calling function
function from data to reals; function according to which the data is ordered
object of class L2ParamFamily
object of class IC
: To determine the size of the observation
symbols, we compute the norm of the IC evaluated at this point.
object of class IC
: one of the ICs from which to take the
risk difference.
object of class IC
: one of the ICs from which to take the
risk difference.
object of class asGRisk
: the risk to take the fifference
from
positive numeric of length 1: the neighborhood radius
positive numeric of length 1: the maximal bias of IC2
.
jittering factor used in case of a DiscreteDistribution
for plotting points of the second argument in a jittered fashion.
jittering tolerance used in case of a DiscreteDistribution
for plotting points of the second argument in a jittered fashion.
stored info from the plot
.plotData
takes argument data
and plots it into the cniper graph.
.getFunCnip
produces a function to compute the risk difference. If
argument b20
is not NULL
, in the risk difference, for IC2
uses the least favorable contamination situation
('over all real Dirac contamination points'), i.e. leading to a bias
of b20
. Otherwise it uses the bias obtaine from a contamination
in the evaluation point.