Coordinate descent methods for the penalized semiparametric additive hazards model
Publication: Research › Report
Standard
Coordinate descent methods for the penalized semiparametric additive hazards model. / Gorst-Rasmussen, Anders; Scheike, Thomas.
Department of Mathematical Sciences, Aalborg University, 2011. 17 p. (Research Report Series; No. R-2011-10).Publication: Research › Report
Harvard
APA
CBE
MLA
Vancouver
Author
Bibtex
}
RIS
TY - RPRT
T1 - Coordinate descent methods for the penalized semiparametric additive hazards model
A1 - Gorst-Rasmussen,Anders
A1 - Scheike,Thomas
AU - Gorst-Rasmussen,Anders
AU - Scheike,Thomas
PB - Department of Mathematical Sciences, Aalborg University
PY - 2011
Y1 - 2011
N2 - For survival data with a large number of explanatory variables,<br/>lasso penalized Cox regression is a popular regularization strategy. However,<br/>a penalized Cox model may not always provide the best fit to data and can<br/>be difficult to estimate in high dimension because of its intrinsic nonlinearity.<br/>The semiparametric additive hazards model is a flexible alternative which is a<br/>natural survival analogue of the standard linear regression model. Building on<br/>this analogy, we develop a cyclic coordinate descent algorithm for fitting the<br/>lasso and elastic net penalized additive hazards model. The algorithm requires<br/>no nonlinear optimization steps and offers excellent performance and stability.<br/>An implementation is available in the R-package ahaz and we demonstrate this<br/>package in a small timing study and in an application to real data.
AB - For survival data with a large number of explanatory variables,<br/>lasso penalized Cox regression is a popular regularization strategy. However,<br/>a penalized Cox model may not always provide the best fit to data and can<br/>be difficult to estimate in high dimension because of its intrinsic nonlinearity.<br/>The semiparametric additive hazards model is a flexible alternative which is a<br/>natural survival analogue of the standard linear regression model. Building on<br/>this analogy, we develop a cyclic coordinate descent algorithm for fitting the<br/>lasso and elastic net penalized additive hazards model. The algorithm requires<br/>no nonlinear optimization steps and offers excellent performance and stability.<br/>An implementation is available in the R-package ahaz and we demonstrate this<br/>package in a small timing study and in an application to real data.
KW - survival
KW - additive hazards
KW - lasso
KW - elasti net
KW - coordinate descent
BT - Coordinate descent methods for the penalized semiparametric additive hazards model
T3 - Research Report Series
T3 - en_GB
ER -