huge: High-Dimensional Undirected Graph Estimation

Share:

Provides a general framework for high-dimensional undirected graph estimation. It integrates data preprocessing, neighborhood screening, graph estimation, and model selection techniques into a pipeline. In preprocessing stage, the nonparanormal(npn) transformation is applied to help relax the normality assumption. In the graph estimation stage, the graph structure is estimated by Meinshausen-Buhlmann graph estimation or the graphical lasso, and both methods can be further accelerated by the lossy screening rule preselecting the neighborhood of each variable by correlation thresholding. We target on high-dimensional data analysis usually d >> n, and the computation is memory-optimized using the sparse matrix output. We also provide a computationally efficient approach, correlation thresholding graph estimation. Three regularization/thresholding parameter selection methods are included in this package: (1)stability approach for regularization selection (2) rotation information criterion (3) extended Bayesian information criterion which is only available for the graphical lasso.

Author
Tuo Zhao, Xingguo Li, Han Liu, Kathryn Roeder, John Lafferty, Larry Wasserman
Date of publication
2015-09-16 10:05:23
Maintainer
Tuo Zhao <tzhao5@jhu.edu>
License
GPL-2
Version
1.2.7

View on CRAN

Man pages

huge
High-dimensional undirected graph estimation
huge.generator
Data generator
huge-internal
Internal huge functions
huge.npn
Nonparanormal(npn) transformation
huge-package
High-Dimensional Undirected Graph Estimation
huge.plot
Graph visualization
huge.roc
Draw ROC Curve for a graph path
huge.select
Model selection for high-dimensional undirected graph...
plot.huge
Plot function for S3 class "huge"
plot.roc
Plot function for S3 class "roc"
plot.select
Plot function for S3 class "select"
plot.sim
Plot function for S3 class "sim"
print.huge
Print function for S3 class "huge"
print.roc
Print function for S3 class "roc"
print.select
Print function for S3 class "select"
print.sim
Print function for S3 class "sim"
stockdata
Stock price of S&P 500 companies from 2003 to 2008

Files in this package

huge
huge/inst
huge/inst/doc
huge/inst/doc/huge.pdf
huge/inst/doc/vignette.Rnw
huge/inst/doc/vignette.pdf
huge/src
huge/src/hugeglasso.c
huge/src/hugeglassoscr.c
huge/src/SFGen.c
huge/src/RIC.c
huge/src/SPMBgraph.c
huge/src/SPMBscr.c
huge/NAMESPACE
huge/data
huge/data/stockdata.rda
huge/data/datalist
huge/R
huge/R/huge.plot.R
huge/R/huge.mb.R
huge/R/huge.select.R
huge/R/huge.glasso.R
huge/R/huge.R
huge/R/huge.ct.R
huge/R/huge.roc.R
huge/R/huge.generator.R
huge/R/huge.npn.R
huge/vignettes
huge/vignettes/huge.pdf
huge/vignettes/vignette.Rnw
huge/MD5
huge/build
huge/build/vignette.rds
huge/DESCRIPTION
huge/man
huge/man/plot.select.Rd
huge/man/stockdata.Rd
huge/man/huge-internal.Rd
huge/man/print.roc.Rd
huge/man/huge.plot.Rd
huge/man/print.sim.Rd
huge/man/plot.roc.Rd
huge/man/plot.huge.Rd
huge/man/huge-package.Rd
huge/man/huge.generator.Rd
huge/man/print.huge.Rd
huge/man/huge.select.Rd
huge/man/plot.sim.Rd
huge/man/huge.roc.Rd
huge/man/huge.npn.Rd
huge/man/huge.Rd
huge/man/print.select.Rd