fastM (version 0.0-4)

Fast Computation of Multivariate M-Estimators

Description

Implements the new algorithm for fast computation of M-scatter matrices using a partial Newton-Raphson procedure for several estimators. The algorithm is described in Duembgen, Nordhausen and Schuhmacher (2016) .

Copy Link

Version

Install

install.packages('fastM')

Monthly Downloads

167

Version

0.0-4

License

GPL (>= 2)

Maintainer

Klaus Nordhausen

Last Published

May 24th, 2018

Functions in fastM (0.0-4)

DUEMBGENshape

Duembgen's Shape Matrix

M-estimator of Location and Scatter Using Weights Coming From the Multivariate t-distribution

MVTMLE0r

Different Algorithms for M-estimation of Scatter Using Weights Coming From the Multivariate t-distribution

MVTMLEsymm

Symmetrized M-estimator of Scatter Using Weights Coming From the t-distribution