rrest: Robust Regularized Estimator (RegMCD) for location and...

In rrlda: Robust Regularized Linear Discriminant Analysis

Description

Computes the Robust Regularized Estimator for location and inverse scatter.

Usage

rrest(data, lambda=0.5, hp=0.75, thresh=0.0001, maxit=10, penalty="L2")

Arguments

data	Matrix or data.frame of observations
lambda	Penalty parameter which controls the sparseness of the resulting inverse scatter matrix. Default is 0.5
hp	Robustness parameter which specifies the amount of observations to be included in the computations. Default is 0.75
thresh	Threshold value controlling the convergence of the iterative algorithm. Default is 0.0001. In most cases this argument does not have to be supplied.
maxit	Maximum number of iterations of the algorithm. Default is 10.
penalty	Type of penalty to be applied. Possible values are "L1" and "L2".

Details

The Robust Regularized Estimator computes a sparse inverse covariance matrix of the given observations by maximization of a penalized likelihood function. The sparseness is controlled by a penalty parameter lambda. Possible outliers are dealt with by a robustness parameter alpha which specifies the amount of observations for which the likelihood function is maximized.

Value

mean	The resulting location estimate.
covi_nocons	The resulting inverse covariance estimate.
subset	An index vector specifying the data subset used (see robustness parameter alpha).
objective	The maximized objective value.
loglik	The maximized (log-)likelihood value.
niter	The number of iterations

Examples

	x <- cbind(rnorm(100), rnorm(100), rnorm(100)) # use first group only
	rr <- rrest(x, lambda=0.2, hp=0.75)
	solve(rr$covi) ## estimated cov matrix

rrlda documentation built on May 2, 2019, 7:23 a.m.