A distribution that is often applied in statistical models for lifetime data is the inverse Gaussian (IG).An important reason for the variety of its applications is that it arises as the distribution of the lifetime regarded as the first hitting time in a Wiener process in Threshold regression (First Hitting Time regression– FHT regression) (Lee and Whitmore, 2006). The main purpose of this thesis is to contribute to the development of the theoretical and mathematical framework of Threshold regression. Firstly, we study in depth the inverse Gaussian distribution within the framework of generalized linear models (GLM). The GLM approach was first suggested by Nelder and Wedderburn (1972) and consists of a unification of linear and non-linear ...