Count network autoregression

dr. Mirko Armillotta; Konstantinos Fokianos

doi:10.1111/jtsa.12728

Count network autoregression

dr. Mirko Armillotta, Konstantinos Fokianos

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

We consider network autoregressive models for count data with a non-random neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference for such models. We consider both cases of fixed and increasing network dimension and we show that quasi-likelihood inference provides consistent and asymptotically normally distributed estimators. The article is complemented by simulation results and a data example.

Original language	English
Pages (from-to)	584-612
Number of pages	29
Journal	Journal of Time Series Analysis
Volume	45
Issue number	4
DOIs	https://doi.org/10.1111/jtsa.12728
Publication status	Published - Jul 2024

Funding

This work was completed when M. Armillotta was with the Department of Mathematics & Statistics at the University of Cyprus. We greatly appreciate comments made by two reviewers on an earlier version of the manuscript. Both authors acknowledge the hospitality of the Department of Mathematics & Statistics at Lancaster University, where this work was initiated. This work has been co-financed by the European Regional Development Fund and the Republic of Cyprus through the Research and Innovation Foundation, under the project INFRASTRUCTURES/1216/0017 (IRIDA). In addition, K. Fokianos acknowledges travel support by CY Initiative of Excellence (grant \u2018Investissements d'Avenir\u2019 ANR-16-IDEX-0008), Project \u2018EcoDep\u2019 PSI-AAP2020-0000000013. This work was completed when M. Armillotta was with the Department of Mathematics & Statistics at the University of Cyprus. We greatly appreciate comments made by two reviewers on an earlier version of the manuscript. Both authors acknowledge the hospitality of the Department of Mathematics & Statistics at Lancaster University, where this work was initiated. This work has been co\u2010financed by the European Regional Development Fund and the Republic of Cyprus through the Research and Innovation Foundation, under the project INFRASTRUCTURES/1216/0017 (IRIDA). In addition, K. Fokianos acknowledges travel support by CY Initiative of Excellence (grant \u2018Investissements d'Avenir\u2019 ANR\u201016\u2010IDEX\u20100008), Project \u2018EcoDep\u2019 PSI\u2010AAP2020\u20100000000013.

Funders	Funder number
CY Initiative of Excellence	PSI‐AAP2020‐0000000013, ANR‐16‐IDEX‐0008
European Regional Development Fund
Research and Innovation Foundation	INFRASTRUCTURES/1216/0017

Access to Document

10.1111/jtsa.12728

Persistent URL (handle)

Persistent link

6 Citations
1 Preprint

Count Network Autoregression
Armillotta, M. & Fokianos, K., 13 Apr 2021, arXiv.org, 63 p.
Research output: Working paper / Preprint › Preprint › Professional

Open Access

Cite this

@article{7e327e746b5547d080123683902cf758,

title = "Count network autoregression",

abstract = "We consider network autoregressive models for count data with a non-random neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference for such models. We consider both cases of fixed and increasing network dimension and we show that quasi-likelihood inference provides consistent and asymptotically normally distributed estimators. The article is complemented by simulation results and a data example.",

author = "Armillotta, {dr. Mirko} and Konstantinos Fokianos",

year = "2024",

month = jul,

doi = "10.1111/jtsa.12728",

language = "English",

volume = "45",

pages = "584--612",

journal = "Journal of Time Series Analysis",

issn = "0143-9782",

publisher = "Wiley-Blackwell",

number = "4",

}

TY - JOUR

T1 - Count network autoregression

AU - Armillotta, dr. Mirko

AU - Fokianos, Konstantinos

PY - 2024/7

Y1 - 2024/7

N2 - We consider network autoregressive models for count data with a non-random neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference for such models. We consider both cases of fixed and increasing network dimension and we show that quasi-likelihood inference provides consistent and asymptotically normally distributed estimators. The article is complemented by simulation results and a data example.

AB - We consider network autoregressive models for count data with a non-random neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference for such models. We consider both cases of fixed and increasing network dimension and we show that quasi-likelihood inference provides consistent and asymptotically normally distributed estimators. The article is complemented by simulation results and a data example.

U2 - 10.1111/jtsa.12728

DO - 10.1111/jtsa.12728

M3 - Article

SN - 0143-9782

VL - 45

SP - 584

EP - 612

JO - Journal of Time Series Analysis

JF - Journal of Time Series Analysis

IS - 4

ER -

Count network autoregression

Abstract

Funding

Access to Document

Persistent URL (handle)

Fingerprint

Research output

Count Network Autoregression

Cite this