The joint models analyse the effect of longitudinal covariates onto the risk of an event. They are composed of two sub-models, the longitudinal and the survival sub-model. For the longitudinal sub-model a multivariate mixed model can be proposed. Whereas for the survival sub-model, a Cox proportional hazards model is proposed, considering jointly the influence of more than one longitudinal covariate onto the risk of the event. The purpose of the work is to extend an estimation method based on a joint likelihood formulation to the case in which the longitudinal submodel is multivariate through the implementation of an Expectation-Maximisation (EM) algorithm.
I modelli congiunti analizzano l’effetto delle covariate longitudinali sul rischio di un evento. Sono composti da due sotto-modelli, quello longitudinale e quello di sopravvivenza. Per il sotto-modello longitudinale si puo proporre un mod- ´ ello misto multivariato, mentre per quello di sopravvivenza viene proposto un modello a rischi proporzionali di Cox, dove le covariate longitudinali influenzano congiuntamente il rischio dell’evento. Lo scopo del lavoro e di estendere un metodo ´ di stima basato sulla massimizzazione della verosimiglianza congiunta al caso in cui il sotto-modello longitudinale e multivariato attraverso l’implementazione di un ` algoritmo Expectation-Maximization (EM).
Mazzoleni, M., Zenga, M. (2018). A multivariate extension of the joint models. In Book of Short Papers SIS 2018 (pp.1124-1129).
A multivariate extension of the joint models
Mazzoleni, M;Zenga, M
2018
Abstract
The joint models analyse the effect of longitudinal covariates onto the risk of an event. They are composed of two sub-models, the longitudinal and the survival sub-model. For the longitudinal sub-model a multivariate mixed model can be proposed. Whereas for the survival sub-model, a Cox proportional hazards model is proposed, considering jointly the influence of more than one longitudinal covariate onto the risk of the event. The purpose of the work is to extend an estimation method based on a joint likelihood formulation to the case in which the longitudinal submodel is multivariate through the implementation of an Expectation-Maximisation (EM) algorithm.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.