AdapEnetClass (version 1.2)

AdapEnetClass-package: A Class of Adaptive Elastic Net Methods for Censored Data

Description

Provides new approaches to variable selection for AFT model.

Details

This package provides new approaches to variable selection for censored data including its high-dimensionality, based on AFT models optimized using regularized weighted least squares. Approaches namely, a weighted elastic net, an adaptive elastic net, and two of their extensions by adding censoring observations as constraints into their model optimization frameworks are provided with both simulated and real (MCL) data examples.

The accelerated failure time (AFT) models have proved useful in many contexts, though heavy censoring (as for example in cancer survival) and high dimensionality (as for example in microarray data) cause difficulties for model fitting and model selection. The package provide new approaches to variable selection for censored data, based on AFT models optimized using regularized weighted least squares. The regularized technique uses a mixture of L1 and L2 norm penalties under two elastic net type approaches. The approaches extend the original approaches proposed by Ghosh (2007), and Hong and Zhang (2010). This package also provides two extended approaches by adding censoring observations as constraints into their model optimization frameworks.

Package:

AdapEnetClass

Type:

Package

Version:

1.2

Date:

2015-10-24

License:

GPL-2

Depends:

imputeYn, glmnet, lars, quadprog

References

Ghosh, S. (2007). Adaptive Elastic Net: An Improvement of Elastic Net to achieve Oracle Properties. Technical Reports, Indiana University-Purdue University, Indianapolis, USA. PR no. 07-01.

Hong, D. and Zhang, F. (2010). Weighted Elastic Net Model for Mass Spectrometry Imaging Processing. Mathematical Modelling of Natural Phenomena, 5, 115-133.

Jin, Z., Lin, D. Y. and Ying, Z. (2006). On least-squares regression with censored data. Biometrika, 93, 147-161.

Khan and Shaw (2015) imputeYn: Imputing the last largest censored observation/observations under weighted least squares. R package version 1.3, https://cran.r-project.org/package=imputeYn.

Khan and Shaw (2015). Variable Selection for Survival Data with a Class of Adaptive Elastic Net Techniques. Statistics and Computing (published online; DOI: 10.1007/s11222-015-9555-8). Also available in http://arxiv.org/abs/1312.2079.

Khan and Shaw (2013). Variable Selection with The Modified Buckley-James Method and The Dantzig Selector for High-dimensional Survival Data. Proceedings 59th ISI World Statistics Congress, 25-30 August 2013, Hong Kong, p. 4239-4244.

Examples

#For full data typically used for AFT models (using imputeYn (2015) package)
dat<-data(n=100, p=10, r=0, b1=c(rep(5,5),rep(0,5)), sig=1, Cper=0)

#mrbj: modified resampling based buckley-james
l<-mrbj(cbind(dat$y, dat$delta) ~ dat$x, mcsize=100, trace=FALSE, gehanonly=FALSE)

#AEnet.aft: adaptive elastic net
wt<-round(l$enet)
ft.1<-AEnet.aft(dat$x, dat$y, dat$delta, weight=wt, lambda2=1, maxit=10)

#AEnetCC.aft: adaptive elastic net with censoring constraints
## Not run: ft.1cc<-AEnetCC.aft(dat$x, dat$y, dat$delta, weight=wt, C=1, 
# s = 0.959596, lambda2=0.5)## End(Not run)

#WEnet.aft: weighted elastic net
#mrbj: modified resampling based buckley-james
## Not run: l<-mrbj(cbind(dat$y, dat$delta) ~ dat$x, mcsize=100, trace=FALSE, gehanonly=TRUE)
## Not run: wt<-l$gehansd
## Not run: ft.2<-WEnet.aft(dat$x, dat$y, dat$delta, weight=wt, lambda2=0.5, maxit=10)

#WEnetCC.aft: weighted elastic net with censoring constraints
## Not run: ft.2cc<-WEnetCC.aft(dat$x, dat$y, dat$delta, weight=wt, C=1, s = 1, lambda2=0.5)