Exponential-Gaussian Distribution and Associated Time Series Models

Accepted: February 2022

Abstract

Exponential-Gaussian distribution has already appeared in the literature and it is widely used in many fields. In this paper, we study its application in time series through a model-based approach. An autoregressive process of order one with exponential-Gaussian distribution as marginals is introduced. Structural aspects of the innovation sequence is derived and analytical properties of the process are studied. Estimation of the parameters is done and the application is established through an illustration with real data.