sugm.select: Model selection for high-dimensional undirected graphical...

View source: R/sugm.select.R

sugm.selectR Documentation

Model selection for high-dimensional undirected graphical models

Description

Implements the regularization parameter selection for high dimensional undirected graphical models. The optional approaches are stability approach to regularization selection (stars) and cross validation selection (cv).

Usage

sugm.select(est, criterion = "stars", stars.subsample.ratio = NULL, 
            stars.thresh = 0.1,rep.num = 20, fold = 5, 
            loss="likelihood", verbose = TRUE)

Arguments

est

An object with S3 class "sugm"

criterion

Model selection criterion. "stars" and "cv" are available for both graph estimation methods. The default value is "stars".

stars.subsample.ratio

The subsampling ratio. The default value is 10*sqrt(n)/n when n>144 and 0.8 when n<=144, where n is the sample size. Only applicable when criterion = "stars".

stars.thresh

The variability threshold in stars. The default value is 0.1. Only applicable when criterion = "stars".

rep.num

The number of subsamplings. The default value is 20.

fold

The number of folds used in cross validation. The default value is 5. Only applicable when criterion = "cv".

loss

Loss to be used in cross validation. Two losses are available: "likelihood" and "tracel2". Default "likelihood". Only applicable when criterion = "cv".

verbose

If verbose = FALSE, tracing information printing is disabled. The default value is TRUE.

Details

Stability approach to regularization selection (stars) is a natural way to select optimal regularization parameter for all three estimation methods. It selects the optimal graph by variability of subsamplings and tends to over-select edges in Gaussian graphical models. Besides selecting the regularization parameters, stars can also provide an additional estimated graph by merging the corresponding subsampled graphs using the frequency counts. The K-fold cross validation is also provided for selecting the parameter lambda, and two loss functions are adopted as follow

likelihood: Tr(Σ Ω) - \log|Ω|

tracel2: Tr(diag(Σ Ω - I)^2).

Value

An object with S3 class "select" is returned:

refit

The optimal graph selected from the graph path

opt.icov

The optimal precision matrix selected.

merge

The graph path estimated by merging the subsampling paths. Only applicable when the input criterion = "stars".

variability

The variability along the subsampling paths. Only applicable when the input criterion = "stars".

opt.index

The index of the selected regularization parameter.

opt.lambda

The selected regularization/thresholding parameter.

opt.sparsity

The sparsity level of "refit".

and anything else inluded in the input est

Note

The model selection is NOT available when the data input is the sample covaraince matrix.

Author(s)

Xingguo Li, Tuo Zhao, Lie Wang, Xiaoming Yuan and Han Liu
Maintainer: Xingguo Li <xingguo.leo@gmail.com>

References

1. T. Cai, W. Liu and X. Luo. A constrained \ell_1 minimization approach to sparse precision matrix estimation. Journal of the American Statistical Association, 2011.
2. B. He and X. Yuan. On non-ergodic convergence rate of Douglas-Rachford alternating direction method of multipliers. Technical Report, 2012.

See Also

sugm and flare-package.

Examples

## load package required
library(flare)

#generate data
L = sugm.generator(d = 10, graph="hub")
out1 = sugm(L$data)

#model selection using stars
#out1.select1 = sugm.select(out1, criterion = "stars", stars.thresh = 0.1)
#plot(out1.select1)

#model selection using cross validation
out1.select2 = sugm.select(out1, criterion = "cv")
plot(out1.select2)

flare documentation built on May 23, 2022, 9:05 a.m.