On accepting the edge-effect (for the inference of ARMA-type processes in Z2)

Chrysoula Dimitriou-Fakalou

Econometrics and Statistics, 2019, vol. 10, issue C, 53-70

Abstract: The edge-effect interrupts the theory of (weakly) stationary processes indexed in the (infinite) two-dimensional lattice. The bias of the maximum likelihood estimators (with asymptotics increasing on both sides), does not seemingly tend to zero faster than their standard error. To deal with it, weights are applied on the computable innovations, such that all the contributions of the same bias are squeezed to become equivalent to that of one observation. As a result, the edge-effect appearance in the form of the speed of the estimators’ bias (to a finite bound) following the augmentation of observations on one axis only, becomes the base for the new solution to the problem. What remains to be seen, is how these weights affect other properties, such as the asymptotic distribution and variance of the proposed estimators.

Keywords: Bias; Edge-effects; Point estimation; Weighted least squares (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S2452306218300091
Full text for ScienceDirect subscribers only. Contains open access articles

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:ecosta:v:10:y:2019:i:c:p:53-70

DOI: 10.1016/j.ecosta.2018.03.001

Access Statistics for this article

Econometrics and Statistics is currently edited by E.J. Kontoghiorghes, H. Van Dijk and A.M. Colubi

More articles in Econometrics and Statistics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().