CovOgk-class {rrcov} | R Documentation |
This class, derived from the virtual class "CovRobust"
accomodates
OGK Estimates of multivariate location and scatter computed by the
algorithm proposed by Marona and Zamar (2002).
Objects can be created by calls of the form new("CovOgk", ...)
,
but the usual way of creating CovOgk
objects is a call to the function
CovOgk
which serves as a constructor.
center
:"vector"
- the final (reweighted) estimate of the location vectorcov
:"matrix"
- the final (reweighted) estimate of the covariance matrixn.obs
:"numeric"
- number of observations used for the estimatesmah
:"Uvector"
- vector of distances computed
relative to the final estimates center
and cov
or NULL. Use the accessor method
getDistance()
.wt
:"vector"
- weights of the observations using the
final estimate of the location and scatter (currently not used) iter
:"numeric"
- number of ortogonalization iterations usedcrit
:call
:"language"
- the call to CovOgk
method
:"character"
- method
used = "Orthogonalized Gnanadesikan-Kettenring Estimator"
singularity
:NULL
of not singular)raw.cov
:"matrix"
the raw
(not reweighted) estimate of covariance matrix raw.center
:"vector"
- the raw
(not reweighted) estimate of the location vectorraw.mah
:"Uvector"
- mahalanobis
distances of the observations based on the raw estimate of the
location and scatter raw.wt
:"Uvector"
- weights of
the observations based on the raw estimate of the location and scatter X
:"Umatrix"
- the data matrix or NULL
Class "CovRobust"
, directly.
Class "Cov"
, by class "CovRobust"
.
No methods defined with class "CovOgk" in the signature.
Valentin Todorov valentin.todorov@chello.at
showClass("CovOgk")