We aim to explore the survival distributions based on the extreme
dispersion, XD, models proposed by Jørgensen (2010). It is suggested that survival times can be modelled within the XD framework by taking log T = Y ~
XD( µ,𝜆 ), where T is the survival time and Y is the extreme dispersion random
variable. We will show how these survival models can be generated using XD
and look at the distribution and properties of the survival time T = eY .
Funding
A new method for transforming data to normality with application to density estimation