A S4 class to store results from performing outlier detection in an ICS context.
Objects can be created by calls of the form new("icsOut", ...)
. But usually objects are created by the function ics.outlier
.
outliers
:Object of class "integer"
. A vector containing ones for outliers and zeros for non outliers.
ics.distances
:Object of class "numeric"
. Vector giving the squared ICS distances of the observations from the invariant coordinates centered with the location estimate specified in S1
.
ics.dist.cutoff
:Object of class "numeric"
. The cut-off for the distances to decide if an observation is outlying or not.
level.dist
:Object of class "numeric"
. The level for deciding upon the cut-off value for the ICS distances.
level.test
:Object of class "numeric"
. The inital level for selecting the invariant coordinates.
method
:Object of class "character"
. Name of the method used to decide upon the number of ICS components.
index
:Object of class "numeric"
. Vector giving the indices of the ICS components selected.
test
:Object of class "character"
. The name of the normality test as specified in the function call.
criterion
:Object of class "numeric"
. Vector giving the marginal levels for the components selection.
adjust
:Object of class "logical"
. Wether the initial level used to decide upon the number of components has been adjusted for multiple testing or not.
type
:Object of class "character"
. Currently always the string "smallprop"
.
mDist
:Object of class "integer"
. Number of simulations performed to decide upon the cut-off for the ICS distances.
mEig
:Object of class "integer"
. Number of simulations performed for selecting the ICS components based on simulations.
S1name
:Object of class "character"
. Name of S1 in the original ics2 object.
S2name
:Object of class "character"
. Name of S2 in the original ics2 object.
For this class the following generic functions are available: print.icsOut
, summary.icsOut
and plot.ics
Aurore Archimbaud and Klaus Nordhausen
ics.outlier