An Algorithm for the Fisher Information Matrix of a VARMAX Process

Abstract

In this paper, an algorithm for Mathematica is proposed for the computation of the asymptotic Fisher information matrix for a multivariate time series, more precisely for a controlled vector autoregressive moving average stationary process, or VARMAX process. Meanwhile, we present briefly several algorithms published in the literature and discuss the sufficient condition of invertibility of that matrix based on the eigenvalues of the process operators. The results are illustrated by numerical computations.

Keywords

• matrix polynomial
• operator eigenvalues
• Fisher information matrix
• stationary VARMAX process
• Mathematica