The expectation-maximization algorithm for autoregressive models with normal inverse Gaussian innovations

In this paper, we study the autoregressive (AR) model with normal inverse Gaussian (NIG) innovations. The NIG distribution is semi heavy-tailed and helpful in capturing extreme observations present data. expectation-maximization (EM) algorithm used to estimate parameters of considered AR(p) model. efficacy estimation procedure shown on simulated data for AR(2) AR(1) models. A comparative presented, where classical algorithms are also incorporated, namely, Yule-Walker conditional least squares methods along EM method parameter estimation. simulation study, maximum likelihood (MLE) by iterative Newton-Raphson compared. real-life applications introduced demonstrated NASDAQ stock market index US gasoline price studies show that residuals good fit financial values as well