A1625
Title: Testing the effect of multiple covariates on the cure rate using martingale difference correlation
Authors: Blanca Monroy-Castillo - Universidade da Coruna (Spain) [presenting]
M Amalia Jacome - Universidade da Coruna (Spain)
Ricardo Cao - University of Coruna (Spain)
Abstract: In survival analysis, there are situations in which not all subjects are susceptible to the final event. Methods are now well-developed to deal with this kind of data, generally known as cure model analysis. Mixture cure models allow for the estimation of the probability of cure and the survival function for uncured subjects. One of the main goals when working with these types of models is to determine if the covariates have any effect on the cure rate. In the nonparametric sense, a test was proposed in a past study. To propose a new test, the focus is on a new measure. Distance correlation, proposed by another study, has been extensively studied and extended. One of these extensions is the martingale difference correlation, which measures the departure from conditional mean independence between a scalar response variable V and a vector predictor variable U. Moreover, martingale difference correlation and its empirical counterpart inherit several desirable features from distance correlation and sample distance correlation. A new significance test for multiple covariates is proposed using martingale difference correlation and its extensions.
