Kim, Namhyun, Wongsa art, Pipat ORCID: https://orcid.org/0000-0002-7611-0383 and Xia, Yingcun
2024.
A dynamic count process.
Journal of Statistical Planning and Inference
, 106187.
10.1016/j.jspi.2024.106187
Item availability restricted. |
PDF
- Accepted Post-Print Version
Restricted to Repository staff only until 26 April 2025 due to copyright restrictions. Download (551kB) |
Abstract
The current paper aims to complement the recent development of the observation-driven models of dynamic counts with a parametric-driven one for a general case, particularly discrete two parameters exponential family distributions. The current paper proposes a finite semiparametric exponential mixture of SETAR processes of the conditional mean of counts to capture the nonlinearity and complexity. Because of the intrinsic latency of the conditional mean, the general additive state-space representation of dynamic counts is firstly proposed then stationarity and geometric ergodicity are established under a mild set of conditions. We also propose to estimate the unknown parameters by using quasi maximum likelihood estimation and establishes the asymptotic properties of the quasi maximum likelihood estimators (QMLEs), particularly T -consistency and normality under the relatively mild set of conditions. Furthermore, the finite sample properties of the QMLEs are investigated via simulation exercises and an illustration of the proposed process is presented by applying the proposed method to the intraday transaction counts per minute of AstraZeneca stock.
Item Type: | Article |
---|---|
Date Type: | Published Online |
Status: | In Press |
Schools: | Business (Including Economics) |
Additional Information: | License information from Publisher: LICENSE 1: Title: This article is under embargo with an end date yet to be finalised. |
Publisher: | Elsevier |
ISSN: | 0378-3758 |
Date of First Compliant Deposit: | 29 April 2024 |
Date of Acceptance: | 18 April 2024 |
Last Modified: | 30 Apr 2024 02:45 |
URI: | https://orca.cardiff.ac.uk/id/eprint/168475 |
Actions (repository staff only)
Edit Item |