monomvn-package {monomvn}R Documentation

Estimation for Multivariate Normal Data with Monotone Missingness

Description

Estimation of multivariate normal data of arbitrary dimension where the pattern of missing data is monotone. Through the use of parsimonious/shrinkage regressions (plsr, pcr, lasso, ridge, etc.), where standard regressions fail, the package can handle an (almost) arbitrary amount of missing data. The current version supports maximum likelihood inference and implementation of a Bayesian version employing a Bayesian lasso. A fully functional stand-alone interface to the Bayesian lasso (from Park & Casella) and ridge regression with model selection via Reversible Jump is also provided

Details

For a fuller overview including a complete list of functions, demos and vignettes, please use help(package="monomvn").

Author(s)

Robert B. Gramacy bobby@statslab.cam.ac.uk

Maintainer: Robert B. Gramacy bobby@statslab.cam.ac.uk

References

Robert B. Gramacy, Joo Hee Lee and Ricardo Silva (2008). On estimating covariances between many assets with histories of highly variable length.
Preprint available on arXiv:0710.5837: http://arxiv.org/abs/0710.5837

http://www.statslab.cam.ac.uk/~bobby/monomvn.html

See Also

monomvn, norm, mvnmle


[Package monomvn version 1.6-1 Index]