| tolEllipsePlot {robustbase} | R Documentation |
Plots the 0.975 tolerance ellipse of the bivariate data set x.
The ellipse is defined by those data points whose distance
is equal to the squareroot of the 0.975 chisquare quantile
with 2 degrees of freedom.
tolEllipsePlot(x, m.cov = covMcd(x), cutoff = NULL, id.n = NULL,
classic = FALSE, tol = 1e-07,
xlab = "", ylab = "",
main = "Tolerance ellipse (97.5%)",
txt.leg = c("robust", "classical"),
col.leg = c("red", "blue"),
lty.leg = c("solid","dashed"))
x |
a two dimensional matrix or data frame. |
m.cov |
an object similar to those of class "mcd"; however
only its components center and cov will be used. If
missing, the MCD will be computed (via covMcd()). |
cutoff |
numeric distance needed to flag data points outside the ellipse. |
id.n |
number of observations to be identified by a label. If
not supplied, the number of observations with distance larger than
cutoff is used. |
classic |
whether to plot the classical distances as well,
FALSE by default. |
tol |
tolerance to be used for computing the inverse, see
solve. Defaults to 1e-7. |
xlab, ylab, main |
passed to plot.default. |
txt.leg, col.leg, lty.leg |
character vectors of length 2 for the
legend, only used if classic = TRUE. |
Peter Filzmoser, Valentin Todorov and Martin Maechler
covPlot which calls tolEllipsePlot() when
desired.
ellipsoidhull and
predict.ellipsoid from package cluster.
data(hbk) hbk.x <- data.matrix(hbk[, 1:3]) mcd <- covMcd(hbk.x) # compute mcd in advance ## must be a 2-dimensional data set: take the first two columns : tolEllipsePlot(hbk.x[,1:2]) ## an "impressive" example: data(telef) tolEllipsePlot(telef, classic=TRUE)