Nonparametric Estimation of Marginal Temporal Functionals in a Multi-State Model

摘要: Multi-state models are generalizations of traditional survival analysis and reliability studies. They common in medical engineering applications where a subject (say patient or machine) is moving through succession states (each representing stage disease progression the condition with time. In addition, several key questions event history multi-variate can be formulated terms staged system making use multi-state extremely broad. While parametric semiparametric to various transitions most approaches study data, this overview paper deals entirely nonparametric methods. we limit our exposition estimation related marginal rather than conditional (e.g., regression) models. We review number methods from recent past dealing hazards, transition state occupation probabilities, entry, exit waiting time distributions also discuss some ongoing future research problems on these topics. Various forms censoring that occur collection data discussed including right interval censoring.