mdpeer: Graph-Constrained Regression with Enhanced Regularization Parameters Selection

Performs graph-constrained regularization in which regularization parameters are selected with the use of a known fact of equivalence between penalized regression and Linear Mixed Model solutions. Provides implementation of three different regression methods where graph-constraints among coefficients are accounted for. 'crPEER' (Partially Empirical Eigenvectors for Regression with Constant Ridge, Constant Ridge PEER) method utilizes additional Ridge term to handle the non-invertibility of a graph Laplacian matrix. 'vrPEER' (Variable Reduction PEER) method performs variable-reduction procedure to handle the non-invertibility of a graph Laplacian matrix. Finally, 'RidgePEER' method employs a penalty term being a linear combination of graph-originated and Ridge-originated penalty terms, whose two regularization parameters are ML estimators from corresponding Linear Mixed Model solution. Notably, in 'RidgePEER' method a graph-originated penalty term allows imposing similarity between coefficients based on graph information given whereas additional Ridge-originated penalty term facilitates parameters estimation: it reduces computational issues arising from singularity in a graph-originated penalty matrix and yields plausible results in situations when graph information is not informative or when it is unclear whether connectivities represented by a graph reflect similarities among corresponding coefficients.

Author
Marta Karas [aut, cre], Damian Brzyski [ctb], Jaroslaw Harezlak [ctb]
Date of publication
2016-11-25 19:48:06
Maintainer
Marta Karas <marta.karass@gmail.com>
License
GPL-2
Version
0.1.0

View on CRAN

Man pages

Adj2Lap
Compute a graph Laplacian matrix from a graph Adjacency...
crPEER
Graph-constrained regression with additional Ridge term to...
dist2sim
Transform Distance matrix to Similarity matrix
L2L.normalized
Compute normalized version of a graph Laplcian matrix
mdpeer
mdpeer: Performs graph-constrained regression with enhanced...
RidgePEER
Graph-constrained estimation with enhanced regulariazation...
RidgePEER.cv
Graph-constrained estimation with regulariazation parameter...
vizu.mat
Visualize matrix data in a form of a heatmap
vrPEER
Graph-constrained regression with variable-reduction...

Files in this package

mdpeer
mdpeer/inst
mdpeer/inst/doc
mdpeer/inst/doc/Introduction_and_usage_examples.R
mdpeer/inst/doc/Introduction_and_usage_examples.html
mdpeer/inst/doc/Introduction_and_usage_examples.Rmd
mdpeer/NAMESPACE
mdpeer/R
mdpeer/R/RidgePEER.R
mdpeer/R/L2Lnormalized.R
mdpeer/R/vizumat.R
mdpeer/R/mdpeer.R
mdpeer/R/GraceTest_C.R
mdpeer/R/dist2sim.R
mdpeer/R/RidgePEER_cv.R
mdpeer/R/A2L.R
mdpeer/R/vrPEER.R
mdpeer/R/crPEER.R
mdpeer/vignettes
mdpeer/vignettes/Introduction_and_usage_examples.Rmd
mdpeer/README.md
mdpeer/MD5
mdpeer/build
mdpeer/build/vignette.rds
mdpeer/DESCRIPTION
mdpeer/man
mdpeer/man/dist2sim.Rd
mdpeer/man/mdpeer.Rd
mdpeer/man/vizu.mat.Rd
mdpeer/man/RidgePEER.cv.Rd
mdpeer/man/RidgePEER.Rd
mdpeer/man/crPEER.Rd
mdpeer/man/L2L.normalized.Rd
mdpeer/man/vrPEER.Rd
mdpeer/man/Adj2Lap.Rd