Display options
Cite
Cao H, Churpek MM, Zeng D, et al. Analysis of the Proportional Hazards Model with Sparse Longitudinal Covariates. J Am Stat Assoc. 2015;110(511):1187-1196doi: 10.1080/01621459.2014.957289.
Cao, H., Churpek, M. M., Zeng, D., & Fine, J. P. (2015). Analysis of the Proportional Hazards Model with Sparse Longitudinal Covariates. Journal of the American Statistical Association, 110(511), 1187-1196. https://doi.org/10.1080/01621459.2014.957289
Cao, Hongyuan, et al. "Analysis of the Proportional Hazards Model with Sparse Longitudinal Covariates." Journal of the American Statistical Association vol. 110,511 (2015): 1187-1196. doi: https://doi.org/10.1080/01621459.2014.957289
Cao H, Churpek MM, Zeng D, Fine JP. Analysis of the Proportional Hazards Model with Sparse Longitudinal Covariates. J Am Stat Assoc. 2015;110(511):1187-1196. doi: 10.1080/01621459.2014.957289. Epub 2015 Nov 07. PMID: 26576066; PMCID: PMC4643320.
Copy Download .nbib Format: NLM
Share it on

J Am Stat Assoc. 2015;110(511):1187-1196. doi: 10.1080/01621459.2014.957289. Epub 2015 Nov 07.

Analysis of the Proportional Hazards Model with Sparse Longitudinal Covariates.

Journal of the American Statistical Association

Hongyuan Cao, Mathew M Churpek, Donglin Zeng, Jason P Fine

Affiliations

  1. Department of Statistics, University of Missouri-Columbia, Columbia, MO, 65201.
  2. Department of Health Studies and Department of Medicine, University of Chicago, Chicago, IL, 60637.
  3. Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27514.

PMID: 26576066 PMCID: PMC4643320 DOI: 10.1080/01621459.2014.957289

Abstract

Regression analysis of censored failure observations via the proportional hazards model permits time-varying covariates which are observed at death times. In practice, such longitudinal covariates are typically sparse and only measured at infrequent and irregularly spaced follow-up times. Full likelihood analyses of joint models for longitudinal and survival data impose stringent modelling assumptions which are difficult to verify in practice and which are complicated both inferentially and computationally. In this article, a simple kernel weighted score function is proposed with minimal assumptions. Two scenarios are considered: half kernel estimation in which observation ceases at the time of the event and full kernel estimation for data where observation may continue after the event, as with recurrent events data. It is established that these estimators are consistent and asymptotically normal. However, they converge at rates which are slower than the parametric rates which may be achieved with fully observed covariates, with the full kernel method achieving an optimal convergence rate which is superior to that of the half kernel method. Simulation results demonstrate that the large sample approximations are adequate for practical use and may yield improved performance relative to last value carried forward approach and joint modelling method. The analysis of the data from a cardiac arrest study demonstrates the utility of the proposed methods.

Keywords: Convergence rates; Cox model; Kernel weighted estimation; Sparse longitudinal covariates

References

  1. Chest. 2012 May;141(5):1170-6 - PubMed
  2. J Clin Oncol. 2010 Jun 1;28(16):2796-801 - PubMed
  3. Stat Med. 1997 Jan 15-Feb 15;16(1-3):239-57 - PubMed
  4. Stat Med. 1996 Aug 15;15(15):1663-85 - PubMed
  5. Biostatistics. 2003 Oct;4(4):633-49 - PubMed
  6. Biometrics. 1994 Dec;50(4):1003-14 - PubMed
  7. Biometrics. 1997 Mar;53(1):330-9 - PubMed
  8. Biostatistics. 2000 Dec;1(4):465-80 - PubMed
  9. Biometrics. 2008 Sep;64(3):950-8 - PubMed

Publication Types

Grant support