A two-component parametric mixture is proposed to model survival after an invasive treatment, when patients may experience different hazards regimes: a risk of early mortality directly related to the treatment and/or the treated condition, and a risk of late death influenced by several exogenous factors. The parametric mixture is based on Weibull distributions for both components. Different sets of covariates can affect the Weibull scale parameters and the probability of belonging to one of the two latent classes. A logarithmic function is used to link explanatory variables to scale parameters while a logistic link is assumed for the probability of the latent classes. Inference about unknown parameters is developed in a Bayesian framework: point and interval estimates are based on posterior distributions, whereas the Schwarz criterion is used for testing hypotheses. The advantages of the approach are illustrated by analyzing data from an aorta aneurysm study.

Farcomeni, A., Nardi, A. (2010). A two component Weibull mixture to model early and late mortality in a Bayesian framework. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 54, 416-428 [10.1016/j.csda.2009.09.007].

A two component Weibull mixture to model early and late mortality in a Bayesian framework

Farcomeni, A;NARDI, ALESSANDRA
2010-01-01

Abstract

A two-component parametric mixture is proposed to model survival after an invasive treatment, when patients may experience different hazards regimes: a risk of early mortality directly related to the treatment and/or the treated condition, and a risk of late death influenced by several exogenous factors. The parametric mixture is based on Weibull distributions for both components. Different sets of covariates can affect the Weibull scale parameters and the probability of belonging to one of the two latent classes. A logarithmic function is used to link explanatory variables to scale parameters while a logistic link is assumed for the probability of the latent classes. Inference about unknown parameters is developed in a Bayesian framework: point and interval estimates are based on posterior distributions, whereas the Schwarz criterion is used for testing hypotheses. The advantages of the approach are illustrated by analyzing data from an aorta aneurysm study.
Pubblicato
Rilevanza internazionale
Articolo
Sì, ma tipo non specificato
Settore MED/01 - Statistica Medica
English
Con Impact Factor ISI
Farcomeni, A., Nardi, A. (2010). A two component Weibull mixture to model early and late mortality in a Bayesian framework. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 54, 416-428 [10.1016/j.csda.2009.09.007].
Farcomeni, A; Nardi, A
Articolo su rivista
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/18781
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 11
social impact