plot.wbaconmv {wbacon}

Plot Diagnostics for an Object of Class wbaconmv

Description

Two plots (selectable by which) are available for an object of class wbaconmv: (1) Robust distance vs. Index and (2) Robust distance vs. Univariate projection.

Usage

## S3 method for class 'wbaconmv'
plot(x, which = 1:2,
    caption = c("Robust distance vs. Index",
    "Robust distance vs. Univariate projection"), hex = FALSE, col = 2,
    pch = 19, ask = prod(par("mfcol")) < length(which) && dev.interactive(),
    alpha = 0.05, maxiter = 20, tol = 1e-5, ...)
SeparationIndex(object, alpha = 0.05, tol = 1e-5, maxiter = 20)

Arguments

x

object of class wbaconmv

which

if a subset of the plots is required, specify a subset of the numbers 1:2, [integer].

caption

captions to appear above the plots; [character] vector of valid graphics annotations. It can be set to "" or NA to suppress all captions.

hex

toogle the hexagonal bin plot on/off [logical] (default: hex = FALSE)

col

color of outliers, [integer] (default: col = 2)

pch

plot character of outliers, [integer] (default: pch = 19)

ask

[logical]; if TRUE, the user is asked before each plot, see par(ask=.).

alpha

[numeric] tuning constant, level of significance, 0 < \alpha < 1; (default: alpha = 0.05).

maxiter

[integer] maximal number of iterations (default: maxiter = 20).

tol

numerical termination criterion, [numeric] (default: tol = 1e-5)

object

object of class wbaconmv

...

additional arguments passed to the method.

Details

The first plot (which = 1) is a standard diagnostic tool which plots the observations' index (1:n) against.the robust (Mahalanobis) distances; see. e.g., Rousseeuw and van Driessen (1999).

The second plot (which = 2) plots the univariate projection of the data which maximizes the separation criterion for clusters of Qui and Joe (2006) against.the robust (Mahalanobis) distances. This plot is due to Willems et al. (2009).

For large data sets, it is recommended to specify the argument hex = TRUE. This option shows a hexagonally binned scatterplot in place of the classical scatterplot.

Value

[no return value]

References

Rousseeuw, P.J. and K. van Driessen (1999). A Fast Algorithm for the Minimum Covariance Determinant, Technometrics 41, 212–223. doi:10.2307/1270566

Qiu, W. and H. Joe (2006). Separation index and partial membership for clustering, Computational Statistics and Data Analysis 50, 585–603. doi:10.1016/j.csda.2004.09.009

Willems, G., H. Joe, and R. Zamar (2009). Diagnosing Multivariate Outliers Detected by Robust Estimators, Journal of Computational and Graphical Statistics 18, 73–91. doi:10.1198/jcgs.2009.0005

See Also

wBACON