Model Specification of a Noncausal 3-D AR Process Using a Causal 3-D AR Model on the Nonsymmetric Half-Space

  • Authors:
  • Byoungseon Choi

  • Affiliations:
  • Department of Applied Statistics, Yonsei University, Seoul, 120-749, Korea bschoi@yonsei.ac.kr

  • Venue:
  • Multidimensional Systems and Signal Processing
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

There exists a causal 3-D AR process on the nonsymmetric half-space having the same autocorrelations as a noncausal 3-D AR process. A formula is presented to relate the AR coefficients of the noncausal 3-D AR process with those of the causal 3-D AR process on the nonsymmetric half-space. The 3-D Yule-Walker equations are derived for causal 3-D AR models on the nonsymmetric half-space, and a computationally efficient order-recursive algorithm is proposed to solve the 3-D Yule-Walker equations. We can easily specify a noncausal 3-D AR process from its autocorrelations using the autocorrelation equivalence relation, the formula of the AR coefficients and the order-recursive algorithm.