Penalized estimation for proportional hazards models with current status data

Minggen Lu, Chin-Shang Li

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We provide a simple and practical, yet flexible, penalized estimation method for a Cox proportional hazards model with current status data. We approximate the baseline cumulative hazard function by monotone B-splines and use a hybrid approach based on the Fisher-scoring algorithm and the isotonic regression to compute the penalized estimates. We show that the penalized estimator of the nonparametric component achieves the optimal rate of convergence under some smooth conditions and that the estimators of the regression parameters are asymptotically normal and efficient. Moreover, a simple variance estimation method is considered for inference on the regression parameters. We perform 2 extensive Monte Carlo studies to evaluate the finite-sample performance of the penalized approach and compare it with the 3 competing R packages: C1.coxph, intcox, and ICsurv. A goodness-of-fit test and model diagnostics are also discussed. The methodology is illustrated with 2 real applications.

Original languageEnglish (US)
JournalStatistics in Medicine
DOIs
StateAccepted/In press - 2017

Fingerprint

Current Status Data
Proportional Hazards Model
Proportional Hazards Models
Regression
Fisher Scoring
Cumulative Hazard Function
Isotonic Regression
Model Diagnostics
Estimator
Cox Proportional Hazards Model
Optimal Rate of Convergence
Variance Estimation
Goodness of Fit Test
Monte Carlo Study
Hybrid Approach
B-spline
Routine Diagnostic Tests
Baseline
Monotone
Methodology

Keywords

  • Current status data
  • Efficient estimation
  • Goodness-of-fit
  • Isotonic regression
  • Monotone B-spline
  • Penalized estimation

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Penalized estimation for proportional hazards models with current status data. / Lu, Minggen; Li, Chin-Shang.

In: Statistics in Medicine, 2017.

Research output: Contribution to journalArticle

@article{830d27fdf1f5497692c4f26ea5fef380,
title = "Penalized estimation for proportional hazards models with current status data",
abstract = "We provide a simple and practical, yet flexible, penalized estimation method for a Cox proportional hazards model with current status data. We approximate the baseline cumulative hazard function by monotone B-splines and use a hybrid approach based on the Fisher-scoring algorithm and the isotonic regression to compute the penalized estimates. We show that the penalized estimator of the nonparametric component achieves the optimal rate of convergence under some smooth conditions and that the estimators of the regression parameters are asymptotically normal and efficient. Moreover, a simple variance estimation method is considered for inference on the regression parameters. We perform 2 extensive Monte Carlo studies to evaluate the finite-sample performance of the penalized approach and compare it with the 3 competing R packages: C1.coxph, intcox, and ICsurv. A goodness-of-fit test and model diagnostics are also discussed. The methodology is illustrated with 2 real applications.",
keywords = "Current status data, Efficient estimation, Goodness-of-fit, Isotonic regression, Monotone B-spline, Penalized estimation",
author = "Minggen Lu and Chin-Shang Li",
year = "2017",
doi = "10.1002/sim.7489",
language = "English (US)",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Penalized estimation for proportional hazards models with current status data

AU - Lu, Minggen

AU - Li, Chin-Shang

PY - 2017

Y1 - 2017

N2 - We provide a simple and practical, yet flexible, penalized estimation method for a Cox proportional hazards model with current status data. We approximate the baseline cumulative hazard function by monotone B-splines and use a hybrid approach based on the Fisher-scoring algorithm and the isotonic regression to compute the penalized estimates. We show that the penalized estimator of the nonparametric component achieves the optimal rate of convergence under some smooth conditions and that the estimators of the regression parameters are asymptotically normal and efficient. Moreover, a simple variance estimation method is considered for inference on the regression parameters. We perform 2 extensive Monte Carlo studies to evaluate the finite-sample performance of the penalized approach and compare it with the 3 competing R packages: C1.coxph, intcox, and ICsurv. A goodness-of-fit test and model diagnostics are also discussed. The methodology is illustrated with 2 real applications.

AB - We provide a simple and practical, yet flexible, penalized estimation method for a Cox proportional hazards model with current status data. We approximate the baseline cumulative hazard function by monotone B-splines and use a hybrid approach based on the Fisher-scoring algorithm and the isotonic regression to compute the penalized estimates. We show that the penalized estimator of the nonparametric component achieves the optimal rate of convergence under some smooth conditions and that the estimators of the regression parameters are asymptotically normal and efficient. Moreover, a simple variance estimation method is considered for inference on the regression parameters. We perform 2 extensive Monte Carlo studies to evaluate the finite-sample performance of the penalized approach and compare it with the 3 competing R packages: C1.coxph, intcox, and ICsurv. A goodness-of-fit test and model diagnostics are also discussed. The methodology is illustrated with 2 real applications.

KW - Current status data

KW - Efficient estimation

KW - Goodness-of-fit

KW - Isotonic regression

KW - Monotone B-spline

KW - Penalized estimation

UR - http://www.scopus.com/inward/record.url?scp=85028926958&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028926958&partnerID=8YFLogxK

U2 - 10.1002/sim.7489

DO - 10.1002/sim.7489

M3 - Article

C2 - 28872695

AN - SCOPUS:85028926958

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

ER -