arXiv subjects
Publications and source records attributed to Kaveh Vakili.
The Projection Congruent Subset (PCS) is new method for finding multivariate outliers. PCS returns an outlyingness index which can be used to construct affine equivariant estimates of multivariate location and scatter. In this note, we derive the finite sample breakdown point of these estimators.
In this note we introduce the M$S_n$ estimator (for Multivariate $S_n$) a new robust estimator of multivariate ranking. Like MVE and MCD it searches for an $h$-subset which minimizes a criterion. The difference is that the new criterion measures the degree of overlap between univariate projections of the data. A primary advantage of this new criterion lies in its relative independence from the configuration of the outliers. A second advantage is that it easily lends itself to so-called "symmetricizing" transformations whereby the observations only enter the objective function through their pairwise differences: this makes our proposal well suited for models with an asymmetric distribution. M$S_n$ is, therefore, more generally applicable than either MVE, MCD or SDE. We also construct a fast algorithm for the M$S_n$ estimator, and simulate its bias under various adversary configurations of outliers.
The Residual Congruent Subset (RCS) is a new method for finding outliers in the linear regression setting. Like many other outlier detection procedures, RCS searches for a subset which minimizes a criterion. The difference is that the new criterion was designed to be insensitive to the outliers. RCS is supported by FastRCS, a fast regression and affine equivariant algorithm which we also detail. Both an extensive simulation study and two real data applications show that FastRCS performs better than its competitors.
The Projection Congruent Subset (PCS) Outlyingness is a new index of multivariate outlyingness obtained by considering univariate projections of the data. Like many other outlier detection procedures, PCS searches for a subset which minimizes a criterion. The difference is that the new criterion was designed to be insensitive to the outliers. PCS is supported by FastPCS, a fast and affine equivariant algorithm which we also detail. Both an extensive simulation study and a real data application from the field of engineering show that FastPCS performs better than its competitors.