PYXIDA Institutional Repository
and Digital Library
 Home
Collections :

Title :Mixture of Weibull regressions as parametric models for exible hazard functions
Creator :Vervita, Aikaterini
Contributor :Karlis, Dimitrios (Επιβλέπων καθηγητής)
Athens University of Economics and Business, Department of Statistics (Degree granting institution)
Type :Text
Extent :93 σ.
Language :en
Abstract :In survival analysis, the idea of hazard function is might be of more interest than the probability density function to a patient who had survived a certain time period and wanted to know something about its survival progress. Thus, in clinical trials the attention is focused on the estimation of hazard function and not in p.d.f.It is easily understood that a hazard function can not be always increasing or decreasing, which happen in many known survival models. It is necessary to befind parametric models which can describe the behavior of the hazard function properly. Most of the distributions that are used very common for the analysis ofsurvival data (e.g. Weibull and exponential) are not able to give hazard functions with exible shapes.
Subject :Clinical trial
HERA trial
Weibull mixture model
EM algorithm
Date Issued :22-02-2017
Licence :

File: Vervita-FT15.pdf

Type: application/pdf