Researchers working on large biomedical and epidemiological cohort observational studies are always seeking for cost-effective designs due to a limited budget. An outcome-dependent sampling (ODS) design, a retrospective sampling scheme where one observes the covariates with a probability depending on the outcome and selects supplemental samples from the most informative and appealing segments, improves the study efficiency while effectively controlling for the budget. For the multivariate data under the ODS (MODS) design, Lu, Longnecker, and Zhou (2017) proposed the inference procedure for a general selection of the continuous responses within a cluster, which is a further generalization of the biased sampling. In this paper, we consider an MODS design for time-to-different-events data under the framework of a semiparametric accelerated failure time (AFT) model with multiple disease outcomes and clustered failure times. We develop an estimating equation approach, based on induced smoothing, for parameter estimation, and the asymptotic properties are established. Extensive simulation studies show that our proposed design and estimator are more efficiency and powerful than other competing estimators. The proposed method is illustrated with a real data set.
|Effective start/end date||2017/08/01 → 2018/07/31|
- Accelerated time model
- Outcome-dependent sampling
- Weighted estimating equations
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.