Generalized inferential models for censored data

Inferential challenges that arise when data are censored have been extensively studied under the classical frameworks. In this paper, we provide an alternative generalized inferential model approach whose output is a data-dependent plausibility function. This construction driven by association between distribution of relative likelihood function at interest parameter and unobserved auxiliary variable. The emerges from suitably calibrated random set designed to predict evaluation requires novel use Kaplan--Meier estimator estimate censoring rather than event distribution. We prove proposed method provides valid inference, least approximately, our real- simulated-data examples demonstrate its superior performance compared existing methods.