Conditional-mean Multiplicative Operator Models for Count Time Series

DOI10.1016/J.CSDA.2023.107885MaRDI QIDQ6420250zbMATH OpenOpenAlexFDO

Authors Christian H. Weiß, Fukang Zhu

Publication date 12 December 2022

Full work available at URL https://doi.org/10.1016/j.csda.2023.107885

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Abstract: Multiplicative error models (MEMs) are commonly used for real-valued time series, but they cannot be applied to discrete-valued count time series as the involved multiplication would not preserve the integer nature of the data. We propose the concept of a multiplicative operator for counts as well as several specific instances thereof, which are then used to develop MEMs for count time series (CMEMs). If equipped with a linear conditional mean, the resulting CMEMs are closely related to the class of so-called integer-valued generalized autoregressive conditional heteroskedasticity (INGARCH) models and might be used as a semi-parametric extension thereof. We derive important stochastic properties of different types of INGARCH-CMEM as well as relevant estimation approaches, namely types of quasi-maximum likelihood and weighted least squares estimation. The performance and application are demonstrated with simulations as well as with two real-world data examples.

Recommendations

• Modelling time series of counts: an INAR approach
• Count Time Series: A Methodological Review
• Conditional maximum likelihood estimation for a class of observation-driven time series models for count data
• Modeling and inference for multivariate time series of counts based on the INGARCH scheme
• Modeling time series of counts with a new class of INAR(1) model

Cited in

(7)

• Bivariate rounded \(\mathbb{Z} \)-valued autoregressive models with flexible auto- and cross-correlations
• A unifying class of compound Poisson integer-valued ARMA and GARCH models
• On an integer-valued stochastic intensity model for time series of counts
• Mean-preserving rounding integer-valued ARMA models
• Negative binomial community network vector autoregression for multivariate integer-valued time series
• Tobit INARMA models for count time series with negative autocorrelation
• Random multiplication versus random sum: autoregressive-like models with integer-valued random inputs

This page was built for publication: Conditional-mean Multiplicative Operator Models for Count Time Series

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6420250)