A Novel Accelerated Failure Time Model: Characterizations, Validation Testing, Different Estimation Methods and Applications in Engineering and Medicine.

In this paper we present a new exponential accelerated failure time model. Some of its properties and characterization results are derived. Different estimation methods are considered for assessing the finite sample behavior of the estimators. Simulation studies for comparing the estimation methods are performed. Finally, we present a novel modified chi-square test for the novel exponential accelerated failure time model in both complete and right censored data cases. The validity of the new model is checked by using the theoretical global of the Nikulin-Rao-Robson. The maximum likelihood method is considered for this purpose. Two simulation studies are performed for assessing the exponential accelerated failure time model and the efficiency of the Nikulin-RaoRobson test statistic, respectively. Three real data sets are considered for illustrating the efficiency of the test statistic in validation. [ABSTRACT FROM AUTHOR]