Least absolute deviations estimation for the accelerated failure time model

Jian Huang, Shuangge Ma, Huiliang Xie

Research output: Journal article publicationJournal articleAcademic researchpeer-review

39 Citations (Scopus)


The accelerated failure time (AFT) model assumes a linear relationship between event time and covariates. We propose a robust weighted least-absolutedeviations (LAD) method for estimation in the AFT model with right-censored data. This method uses the Kaplan-Meier weights in the LAD objective function to account for censoring. We show that the proposed estimator is root-n consistent and asymptotically normal under appropriate assumptions. It can also be easily computed using existing software, which makes it especially useful for data with medium to high dimensional covariates. The proposed method is evaluated using simulations and demonstrated on two clinical data sets.
Original languageEnglish
Pages (from-to)1533-1548
Number of pages16
JournalStatistica Sinica
Issue number4
Publication statusPublished - 1 Oct 2007
Externally publishedYes


  • Asymptotic normality
  • Kaplan-Meier weights
  • Least absolute deviations
  • Right censored data
  • Robust regression

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'Least absolute deviations estimation for the accelerated failure time model'. Together they form a unique fingerprint.

Cite this