B. E. Monroy-Castillo, M. A. Jácome, R. Cao
In survival analysis, not all subjects are necessarily susceptible to the event of interest. Cure models address this issue by distinguishing between cured and uncured individuals. In particular, mixture cure models estimate both the probability of cure and the survival function of uncured subjects. A fundamental question in these models is whether covariates influence the cure rate. Although a non-parametric test based on the martingale difference correlation has been proposed to assess the effect of a single covariate, this work extends the approach to consider multiple covariates simultaneously. Specifically, we introduce a test based on partial martingale difference correlation that allows for a more comprehensive assessment of the effects of covariates on the cure rate.
Palabras clave: Martingale difference correlation, mixture cure models, nonparametric test
Programado
Estimación no paramétrica
12 de junio de 2025 19:00
Sala de prensa (MR 13)