Spectral density estimation for random processes with stationary increments
Document Type
Article
Publication Date
2024
Department/School
Economics
Publication Title
Applied Stochastic Models in Business and Industry
Abstract
Spectral density analysis plays an important role in studying a stationary random process on a real line. In this paper, we extend this discussion for the random process with stationary increments. We investigate the properties of the method of moments structure function estimation, and propose a nonparametric spectral density function estimator. Our numerical results show that the proposed spectral density estimator performs comparable with the parametric counterpart when the underlying process is assumed to be band-limited. Additionally, this method is applied to analyze US Housing Starts Data, where the hidden periodicities are detected, providing consistent conclusions with previous economic studies.
Recommended Citation
Chen, W., Huang, C., Zhang, H., & Schaffer, M. (2024). Spectral density estimation for random processes with stationary increments. Applied Stochastic Models in Business and Industry, 40(4), 960–978. https://doi.org/10.1002/asmb.2857
Comments
M. Schaffer is a faculty member in EMU's Department of Economics.