LWradius: Wilkinson's default leader-partitioning radius

In probout: Unsupervised Multivariate Outlier Probabilities for Large Datasets

Description

Wilkinson's default leader-partitioning radius.

Usage

LWradius( n, p)

Arguments

n	The number of observations (rows) in the data.
p	The number of variables (columns) in the data; p = 1 if univariate.

Value

Wilkinson's default leader partitioning radius 0.1/(log(n)^(1/p)).

References

L. Wilkinson (2016), Visualizing Outliers, Technical Report, University of Illinois at Chicago, https://www.cs.uic.edu/~wilkinson/Publications/outliers.pdf.

See Also

leader

Examples

 x1 <- rnorm(10000)
 LWradius(length(x1),1)

 LWradius(nrow(faithful),ncol(faithful))

probout documentation built on Feb. 11, 2022, 5:10 p.m.