gms | German Medical Science

Competing Risks Models have a various field of applications in medical and public health studies. A challenging clue for applying cause-specific survival models yield on the problem of missing and misclassification in cause of death. The masked cause of death is related to incomplete or only partial identifiable in formation of death certificates. Different Bayesian approaches [1] e.g. the mixture cure model [2] are proposed to account for that problem. Another question is related to adequate estimates for long-term Survival in respect to the limitation of lifetime among all risks. As a new parametric distribution the long-term exponential geometric distribution (LEG) introduced by Roman et al. 2012 [3] can be considered. The LEG will be defined as three-parameters lifetime distribution with decreasing hazard function with mixed model characteristics. One of challencing remarks is to predict the conditional failure time function for future events or items depending on times of a few early failures.

The main purpose of this work is to compare the LEG with alternative parametric versions like Weibull distribution, or the simple Exponential distribution for long-term survival estimates. Data analysis will be realized with e.g. UK Stroke Register Data and R Statistical Software. As on remarkable conclusion one would expect the best fitting of the LEG for the long-term survival regarding to Weibull and Exponential distribution.