An entropy transformed Weibull extended distribution for real world data analytics

Proliferation of data all over the world requires the development of advance methodologies. These methodologies provide frameworks for the analysis of complex data with a high degree of accuracy. In response to the need for accurate methodologies, this study proposes a new distribution using entropy transformation, called the entropy transformed generalized new extended Weibull distribution. The graphical and numerical estimates of some of its structural properties show that it can model data with varying degrees of asymmetry and peakedness. Four different estimation methods are used to estimate the parameters of the distribution. Upon assessment of the estimators via a simulation study, maximum likelihood method is found to be better suited for estimating the parameters of the model, though all the methods are consistent and asymptotically unbiased. Using the new distribution, regression models with different structures, are constructed. The adaptability and practical usefulness of the distribution and its regression models are demonstrated using five real world data sets from the fields of health, engineering, insurance, finance and hydrology. The results show that the novel method developed is a competitive alternative for modeling data from different fields, exhibiting varying characteristics.