|
Abstract
|
The paper proposes a new family of continuous distributions called the extended odd half
Cauchy-G. It is based on the T − X construction of Alzaatreh et al. (2013) by considering half Cauchy distribution for T and the exponentiated G(x;ξ) as the distribution of X.
Several particular cases are outlined and a number of important statistical characteristics of
this family are investigated. Parameter estimation via several methods, including maximum
likelihood, is discussed and followed up with simulation experiments aiming to asses their
performances. Real life applications of modeling two data sets are presented to demonstrate
the advantage of the proposed family of distributions over selected existing ones. Finally,
a new regression model is proposed and its application in modeling data in the presence of
covariates is presented
|