A fast algorithm for the accelerated failure time model with high-dimensional time-to-event data

Taehwa Choi, Sangbum Choi

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


We propose the logistic-kernel smoothing procedure for the semiparametric accelerated failure time (AFT) model with high-dimensional right-censored data. The resulting estimating procedure permits fast and accurate computation of regression parameter estimates and standard errors while preserving the same asymptotic properties as those from the non-smoothed rank estimating function. In addition, we provide an efficient numerical algorithm for obtaining a complete regularization path to facilitate adaptive variable selection in the AFT model. This can be done by using a second-order approximation of the smoothed estimating function and coordinate decent algorithm. Through extensive simulation studies, we examine several well-known penalties and show that our method is robust and computationally efficient with minimal loss of precision. Application to primary biliary cirrhosis (PBC) data demonstrates the utility of the proposed method in routine survival data analysis.

Original languageEnglish
Pages (from-to)3385-3403
Number of pages19
JournalJournal of Statistical Computation and Simulation
Issue number16
Publication statusPublished - 2021

Bibliographical note

Funding Information:
This work was supported by the Korea University [grant number K2009281] and the National Research Foundation (NRF) of Korea [grant numbers 2019R1F1A1052239 and 2019R1A4A1028134].

Publisher Copyright:
© 2021 Informa UK Limited, trading as Taylor & Francis Group.


  • Coordinate descent
  • kernel smoothing
  • linear model
  • logistic loss
  • regularization
  • survival analysis
  • variable selection

ASJC Scopus subject areas

  • Statistics and Probability
  • Modelling and Simulation
  • Statistics, Probability and Uncertainty
  • Applied Mathematics


Dive into the research topics of 'A fast algorithm for the accelerated failure time model with high-dimensional time-to-event data'. Together they form a unique fingerprint.

Cite this