DetectOutliersViaMVE: Use the minimum volume ellipsoid to detect outliers

Description Usage Arguments Value Author(s) References

Description

See Sec. 4.6.1 of "Risk and Asset Allocation" - Springer (2005), by A. Meucci for the theory and the routine implemented below

Usage

1
  DetectOutliersViaMVE(corruptSample)

Arguments

corruptSample

a matrix of returns with outlier data. Rows are observations, columns are assets.

Value

a list containing: plotdata a matrix of data used to plot minimum volume ellipsoid as a function of its length cutofflist an ordering of observations with the highest Mahalanobis distance (i.e. ordering of outliers by their index )#' numOutliers returns the number of outliers based on the slope of the minimum volume ellipsoid as a function of sample data

Author(s)

Ram Ahluwalia ram@wingedfootcapital.com

References

http://www.symmys.com See Meucci script for "S_HighBreakdownMVE.m"


R-Finance/Meucci documentation built on May 8, 2019, 3:52 a.m.