An empirical comparison of parametric and semiparametric time series regression models for overdispersed count data. Issue 4 (19th May 2022)

• Record Type: Journal Article
• Authors: Ghahramani, M.; White, S. S.; de Leon, A. R.
• Is Part Of: Journal of statistics & management systems. Volume 25:Issue 4(2022)
• Page Start: 879
• Page End: 905
• Publication Date: 2022-05-19
• Subjects: 62M10; Count data -- Estimating function -- INGARCH -- Overdispersion -- Regression -- Time series; Statistics -- Periodicals; Mathematical models -- Periodicals; Mathematical models; Statistics; Periodicals; 519.5
• DOI: 10.1080/09720510.2021.1960550
• Languages: English
• ISSNs: 0972-0510

Abstract

Abstract: Count time series regression is of interest in diverse applications. Count data may be marginally, as well as conditionally overdispersed, in addition to being serially dependent. We propose a fully parametric approach and a semiparametric approach (in the Godambeinformation sense), and compare model performance in simulation studies. Estimators from both approaches exhibit large relative bias, but their variability was similar. Our empirical study shows that while our semiparametric approach method is promising as a robust alternative to fully parametric count time series regression modelling, bias correction is needed.