Answers are grounded in this paper and cite their sources.
This paper considers regression analysis of multivariate right-censored data under a semiparametric probit model with a positive, mean-one shared frailty. The model describes dependence arising from a common scale of the transformed residuals. For inference, we propose a sieve maximum likelihood estimation method based on monotone splines and develop an expectation–conditional maximization algorithm using normal and multinomial data augmentation. The algorithm yields closed-form conditional updates for the regression and spline coefficients. Identifiability is established within specified log-normal and gamma frailty families. Under stated regularity, approximation, and optimization conditions, approximate global sieve maximizers are shown to be consistent, and the corresponding regression estimators are asymptotically normal and semiparametrically efficient. Simulation studies assess the finite-sample performance of the proposed estimation procedure, and an application to paired eye data from the Diabetic Retinopathy Study illustrates its use.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: