Skip to main content

Advertisement

SpringerLink
Log in

Cox Regression with Covariates Missing Not at Random

  • Published:
Statistics in Biosciences Aims and scope Submit manuscript

Abstract

This paper considers estimation under the Cox proportional hazards model with right-censored event times in the presence of covariates missing not at random (MNAR). We propose an approach derived from likelihood estimation utilizing supplementary information. We show that available additional information not only helps to account appropriately for the missing covariates but also leads to estimation procedures which are natural and easy to implement. A medical example is used throughout the paper to motivate the problem and to illustrate the proposed methodology.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Andersen PK, Borgan O, Gill RD, Keiding N (1992) Statistical models based on counting processes. Springer, New York

    Google Scholar 

  2. Bang H, Robins JM (2005) Doubly robust estimation in missing data and causal inference models. Biometrics 61:962–973

    Article  MathSciNet  MATH  Google Scholar 

  3. Breslow NE (1972) Discussion of the paper by DR Cox. J R Stat Soc B 34:216–217

    MathSciNet  Google Scholar 

  4. Canadian Tuberculosis Standards 6th edn (2007) Edited by Long, R Canadian Lung Association, Canadian Thoracic Society and Tuberculosis Prevention and Control Centre for Infectious Disease Prevention and Control, Health Canada

  5. Chen MH, Ibrahim JG, Shao QM (2009) Maximum likelihood inference for the Cox regression model with applications to missing covariates. J Multivar Anal 100:2018–2030

    Article  MathSciNet  MATH  Google Scholar 

  6. Chen HY, Little RJA (1999) Proportional hazards regression with missing covariates. J Am Stat Assoc 94:896–908

    Article  MathSciNet  MATH  Google Scholar 

  7. Cook VJ, Hernandex-Garduno E, Hu XJ, Elwood RK, FitzGerald JM (2005) The influence of cluster-status of source cases on contact evaluation and the development of secondary active tuberculosis. Proceedings of the American Thoracic Society (PATS) 2 Abstract Issue

  8. Cox DR (1972) Regression models and life tables (with discussion). J R Stat Soc B 34:187–220

    MATH  Google Scholar 

  9. Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc B 39:1–22

    MathSciNet  MATH  Google Scholar 

  10. Efron B, Tibshirani RJ (1993) An introduction to the bootstrap. Monographs on statistics and applied probability, vol 57. Chapman & Hall/CRC, London/Boca Raton

    MATH  Google Scholar 

  11. Herring AH, Ibrahim JG (2001) Likelihood-based methods for missing covariates in the Cox proportional hazards model. J Am Stat Assoc 96:292–302

    Article  MathSciNet  MATH  Google Scholar 

  12. HIV/AIDS Epi Updates November 2007. Centre for Infectious Disease Prevention and Control, Public Health Agency of Canada

  13. Hu XJ, Lawless JF (1996) Estimation from truncated lifetime data with supplementary information on covariates and censoring times. Biometrika 83:747–61

    Article  MathSciNet  MATH  Google Scholar 

  14. Hu XJ, Lawless JF (1997) Pseudo-likelihood estimation in a class of problems with response-related missing covariates. Can J Stat 25:125–42

    Article  MathSciNet  MATH  Google Scholar 

  15. Li Y, Dicker L, Zhao S (2010) A new class of Dantzig selectors for censored linear regression models. Harvard University Biostatistics Working Paper Series (March 2, 2010)

  16. Lin DY, Ying Z (1993) Cox regression with incomplete covariate measurements. J Am Stat Assoc 88:1341–1349

    Article  MathSciNet  MATH  Google Scholar 

  17. Little RJA, Rubin DB (2002) Statistical analysis with missing data. Wiley series in probability and statistics. Wiley, New York

    Google Scholar 

  18. Nan B, Kalbfleisch JD, Yu M (2009) Asymptotic theory for the semiparametric accelerated failure time model with missing data. Ann Stat 37:2351–2376

    Article  MathSciNet  MATH  Google Scholar 

  19. Paik MC, Tsai WY (1997) On using the Cox proportional hazards model with missing covariates. Biometrika 84:579–593

    Article  MathSciNet  MATH  Google Scholar 

  20. Qi L, Wang CY, Prentice RL (2005) Weighted estimators for proportional hazards regression with missing covariates. J Am Stat Assoc 100:1250–1263

    Article  MathSciNet  MATH  Google Scholar 

  21. Reichler MR, Bur S, Reves R, Mangura B, Thompson V, Ford J, Castro KG (2003) Results of testing for human immunodeficiency virus infection among recent contacts of infectious tuberculosis cases in the United States. Int J Tuberc Lung Dis 7(12):5471–5478

    Google Scholar 

  22. Robins JM, Rotnitzky A, Zhao LP (1994) Estimation of regression coefficients when some regressors are not always observed. J Am Stat Assoc 89:846–866

    Article  MathSciNet  MATH  Google Scholar 

  23. Scharfstein DO, Rotnitzky A, Robins JM (1999) Adjusting for nonignorable drop-out using semiparametric nonresponse models. J Am Stat Assoc 94:1096–1120

    Article  MathSciNet  MATH  Google Scholar 

  24. Suzuki K (1985) Estimation method of lifetime based on the record of failures during the warranty period. J Am Stat Assoc 80:68–72

    Article  MATH  Google Scholar 

  25. Tsiatis AA (2006) Semiparametric theory and missing data. Springer series in statistics. Springer, Berlin

    MATH  Google Scholar 

  26. Zeng D, Cai J (2005) Asymptotic results for maximum likelihood estimators in joint analysis of repeated measurements and survival time. Ann Stat 33:2132–2163

    Article  MathSciNet  MATH  Google Scholar 

  27. Zhou H, Pepe MS (1995) Auxiliary covariate data in failure time regression. Biometrika 82:139–149

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. BC Centre for Disease Control, University of British Columbia, 655 West 12th Avenue, Vancouver, British Columbia, V5Z 4R4, Canada

    Victoria J. Cook

  2. Department of Statistics and Acturial Sciences, Simon Fraser University, Burnaby, British Columbia, V5A 1S6, Canada

    X. Joan Hu & Tim B. Swartz

Authors
  1. Victoria J. Cook
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. X. Joan Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tim B. Swartz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to X. Joan Hu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cook, V.J., Hu, X.J. & Swartz, T.B. Cox Regression with Covariates Missing Not at Random. Stat Biosci 3, 208–222 (2011). https://doi.org/10.1007/s12561-010-9031-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12561-010-9031-0

Keywords

Search

Navigation