Scalable algorithms for semiparametric accelerated failure time models in high dimensions

Semiparametric accelerated failure time (AFT) models are a useful alternative to Cox proportional hazards models, especially when the assumption of constant hazard ratios is untenable. However, rank‐based criteria for fitting AFT models are often nondifferentiable, which poses a computational challe...

Full description

Saved in:
Bibliographic Details
Published in:Statistics in medicine Vol. 41; no. 6; pp. 933 - 949
Main Authors: Suder, Piotr M., Molstad, Aaron J.
Format: Journal Article
Language:English
Published: England Wiley Subscription Services, Inc 15.03.2022
Subjects:
accelerated failure time model
Algorithms
bilevel variable selection
Computer Simulation
convex optimization
Gehan estimator
Humans
Least-Squares Analysis
Models, Statistical
Proportional Hazards Models
semiparametrics
survival analysis
accelerated failure time model
convex optimization
Gehan estimator
semiparametrics
survival analysis
bilevel variable selection
ISSN:0277-6715, 1097-0258, 1097-0258
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Semiparametric accelerated failure time (AFT) models are a useful alternative to Cox proportional hazards models, especially when the assumption of constant hazard ratios is untenable. However, rank‐based criteria for fitting AFT models are often nondifferentiable, which poses a computational challenge in high‐dimensional settings. In this article, we propose a new alternating direction method of multipliers algorithm for fitting semiparametric AFT models by minimizing a penalized rank‐based loss function. Our algorithm scales well in both the number of subjects and number of predictors, and can easily accommodate a wide range of popular penalties. To improve the selection of tuning parameters, we propose a new criterion which avoids some common problems in cross‐validation with censored responses. Through extensive simulation studies, we show that our algorithm and software is much faster than existing methods (which can only be applied to special cases), and we show that estimators which minimize a penalized rank‐based criterion often outperform alternative estimators which minimize penalized weighted least squares criteria. Application to nine cancer datasets further demonstrates that rank‐based estimators of semiparametric AFT models are competitive with estimators assuming proportional hazards in high‐dimensional settings, whereas weighted least squares estimators are often not. A software package implementing the algorithm, along with a set of auxiliary functions, is available for download at github.com/ajmolstad/penAFT.
Bibliography:Funding information
ADMM, alternating direction method of multipliers; AFT, accelerated failure time; KIRC, kidney renal clear cell carcinoma.
National Science Foundation, DMS‐2113589
Abbreviations
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0277-6715
1097-0258
1097-0258
DOI:10.1002/sim.9264