Robust Laplace Periodogram and Its Asymptotic Properties for Frequency Estimation of 2-Dimensional Superimposed Sinusoidal Model

Abstract

In this paper, we consider the problem of robust estimation of frequencies of a 2-dimensional superimposed sinusoidal model. We propose a 2-dimensional sequential Laplace periodogram for the frequency estimation problem and derive it’s asymptotic distribution. The proposed approach and the derived asymptotic results extend the Laplace periodogram approach of Li [1,2] to 2-dimensional sinusoidal models. Empirical studies illustrate the usefulness and advantages of the proposed approach as compared to usual periodogram approach.