Abstract
In many clinical studies where time to failure is of primary interest, patients may fail or die from one of many causes where failure time can be right censored. In some circumstances, it might also be the case that patients are known to die but the cause of death information is not available for some patients. Under the assumption that cause of death is missing at random, we compare the Goetghebeur and Ryan (1995, Biometrika, 82, 821–833) partial likelihood approach with the Dewanji (1992, Biometrika, 79, 855–857)partial likelihood approach. We show that the estimator for the regression coefficients based on the Dewanji partial likelihood is not only consistent and asymptotically normal, but also semiparametric efficient. While the Goetghebeur and Ryan estimator is more robust than the Dewanji partial likelihood estimator against misspecification of proportional baseline hazards, the Dewanji partial likelihood estimator allows the probability of missing cause of failure to depend on covariate information without the need to model the missingness mechanism. Tests for proportional baseline hazards are also suggested and a robust variance estimator is derived.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
P. D. Allison (1995) Survival Analysis Using the SAS System: A Practical Guide The SAS Institute Cary
J. Andersen E. Goetghebeur L. Ryan (1996) ArticleTitleMissing cause of death information in the analysis of survival data Statistics in Medicine 15 1191–2201
P. K. Andersen O. Borgan R. D. Gill N. Keiding (1997) Statistical Models Based on Counting Processes Springer-Verlag New York
P. K. Andersen R. D. Gill (1982) ArticleTitle“Cox’s regression model for counting processes: a large sample study” Annals of Statistics 10 1100–1120
P. J. Bickel C. A. Klaasen Y. Ritov J. A. Wellner (1993) Efficient and Adaptive Estimation for Semiparametric Models John Hopkins University Press Baltimore
D. R. Cox (1975) ArticleTitlePartial likelihood Biometrika 62 269–276
D. R. Cox D. Oakes (1984) Analysis of Survival Data Chapman Hall New York
A. Dewanji (1992) ArticleTitleA note on a test for competing risks with missing failure type Biometrika 79 855–857
A. Dewanji D. Sengupta (2003) ArticleTitleEstimation of competing risks with general missing pattern in failure types Biometrics 59 1063–1070
T. R. Fleming D. P. Harrington (1991) Counting Processes and Survival Analysis Wiley New York
B. J. Flehinger B. Reiser E. Yashchin (1998) ArticleTitle“Survival with competing risks and masked causes of failure” Biometrika 85 151–164
R. D. Gill S. Johansen (1990) ArticleTitle“A survey of product-integration with a view towards application in survival analysis” Annals of Statistics 18 1501–1555
E. Goetghebeur L. Ryan (1995) ArticleTitle“Analysis of competing risks survival data when some failure types are missing” Biometrika 82 821–833
P. M. Grambsch T. M. Therneau (1994) ArticleTitle“Proportional hazards tests and diagnostics based on weighted residuals” Biometrika 81 515–526
J. D. Holt (1978) ArticleTitle“Competing risk analyses with special reference to matched pair experiments” Biometrika 65 159–165
J. D. Kalbfleisch R. L. Prentice (1980) The Statistical Analysis of Failure Time Data Wiley New York
D. Y. Lin L. J. Wei (1989) ArticleTitle“The robust inference for the Cox proportional hazards model” Journal of the American Statistical Association 84 1074–1078
K. Lu A. A. Tsiatis (2001) ArticleTitle“Multiple imputation methods for estimating regression coefficients in the competing risks model with missing cause of failure” Biometrics 57 1191–1197
W. K. Newey (1990) ArticleTitle“Semiparametric efficiency bounds” Journal of Applied Econometrics 5 99–135
R. L. Prentice J. D. Kalbfleisch (1978) ArticleTitle“The analysis of failure times in the presence of competing risks” Biometrics 34 541–554
J. M. Robins A. Rotnitzky L. P. Zhao (1994) ArticleTitle“Estimation of regression coefficients when some regressors are not always observed” Journal of the American Statistical Association 89 846–866
D. R. Rubin (1976) ArticleTitle“Inference and missing data” Biometrika 63 581–592
A. A. Tsiatis M. Davidian B. McNeney (2002) ArticleTitle“Multiple imputation methods for testing different treatment differences in survival distributions with missing cause of failure” Biometrika 89 238–244
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lu, K., Tsiatis, A.A. Comparison Between Two Partial Likelihood Approaches for the Competing Risks Model with Missing Cause of Failure. Lifetime Data Anal 11, 29–40 (2005). https://doi.org/10.1007/s10985-004-5638-0
Received:
Revised:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10985-004-5638-0