plot.mahalDist function

Plot Mahalanobis distance for a fitted smn.lmm or smsn.lmm

Plot method for objects of class "mahalDist". For the total Mahalanobis distance, it gives a quantile for outlier detection, based on the Mahalanobis distance theoretical distribution.

## S3 method for class 'mahalDist'
plot(x, fitobject, type, level = 0.99, nlabels = 3, ...)

Arguments

• x: An object inheriting from class mahalDist, representing the Mahalanobis distance from a fitted scale mixture of (skew) normal linear mixed model.
• fitobject: Optional. An object inheriting from class SMN or SMSN, representing the fitted scale mixture of (skew) normal linear mixed model that was used for calculating the Mahalanobis distance.
• type: Optional. Either "total" (default), for the standard Mahalanobis distance, "error", for the error term of the decomposition, or "b" for the random effect term of the decomposition. For details see mahalDist.
• level: An optional numeric value in $(0,1)$ indicating the level of the quantile. It only has utility if type="total". Default is 0.99.
• nlabels: Number of observations that should be labeled. Default is 3.
• ...: Additional arguments.

Returns

A ggplot object, plotting the index versus the Mahalanobis distance, if all subject have the same number of observations; or plotting the number of observations per subject versus the Mahalanobis, otherwise.

Author(s)

Fernanda L. Schumacher, Larissa A. Matos and Victor H. Lachos

See Also

ggplot , mahalDist , smn.lmm , smsn.lmm

Examples

fm1 = smn.lmm(distance ~ age+Sex, data=nlme::Orthodont, groupVar="Subject")
plot(mahalDist(fm1), nlabels=2)

#the estimated quantile is stored at the attribute "info" of the plot object
plotMD = plot(mahalDist(fm1))
attr(plotMD, "info")