CMStatistics 2020: Start Registration
View Submission - CMStatistics
Title: Modeling and analysis of data with confounding covariates and crossing of the hazard functions Authors:  Ruta Levuliene - Vilnius University (Lithuania) [presenting]
Vilijandas Bagdonavicius - Faculty of Mathematics and Informatics (Lithuania)
Abstract: Parametric models for the analysis of survival data with a possible crossing of hazard rates related to two treatment groups are introduced. A strategy for survival improvement through the application of time-varying treatment is discussed. Complete and right-censored data with possible confounding covariates are considered. Estimators of the crossing points are given. Chi-squared type goodness-of-fit tests for the considered models are given. Parametric tests for the absence of crossing of survival functions (and also for crossing of the hazard functions) hypothesis are proposed. For models with several baseline distributions, the power functions of the tests were investigated by simulation. Moreover, real and synthetic data analysis is presented.