Semiparametric estimation for the transformation model with length-biased data and covariate measurement error

ABSTRACT

Analysis of survival data with biased samples caused by left-truncation or length-biased sampling has received extensive interest. Many inference methods have been developed for various survival models. These methods with ignorance of mismeasurement, however, may produce different estimations and yield misleading conclusions when survival data are typically error-contaminated. Although error-prone survival data commonly arise in practice, little work has been available in the literature for handling length-biased data with measurement error. In survival analysis, methods of analyzing the transformation model with those complex features have not been fully explored. In this paper, we develop a valid inference method under the transformation model. We establish asymptotic results for the proposed estimators. The proposed method enjoys appealing features in that there is no need to specify the distribution of the covariates and the increasing function in the transformation model. Numerical studies are reported to assess the performance of the proposed method.

KEYWORDS:

• Length-based sampling
• measurement error
• prevalent cohort
• survival analysis
• transformation model

AMS SUBJECT CLASSIFICATION:

• 62N01

Acknowledgments

The author would like to extend great gratitude to an Editor, an Associate Editor and two referees for their valuable suggestions and useful comments to make this paper better.

Disclosure statement

No potential conflict of interest was reported by the author.

ORCID

Li-Pang Chen  http://orcid.org/0000-0001-5440-5036