- search hit 1 of 1
Evaluating approximate point forecasting of count processes
Please always quote using this URN: urn:nbn:de:bvb:20-opus-196929
- In forecasting count processes, practitioners often ignore the discreteness of counts and compute forecasts based on Gaussian approximations instead. For both central and non-central point forecasts, and for various types of count processes, the performance of such approximate point forecasts is analyzed. The considered data-generating processes include different autoregressive schemes with varying model orders, count models with overdispersion or zero inflation, counts with a bounded range, and counts exhibiting trend or seasonality. WeIn forecasting count processes, practitioners often ignore the discreteness of counts and compute forecasts based on Gaussian approximations instead. For both central and non-central point forecasts, and for various types of count processes, the performance of such approximate point forecasts is analyzed. The considered data-generating processes include different autoregressive schemes with varying model orders, count models with overdispersion or zero inflation, counts with a bounded range, and counts exhibiting trend or seasonality. We conclude that Gaussian forecast approximations should be avoided.…
Author: | Annika Homburg, Christian H. Weiß, Layth C. Alwan, Gabriel Frahm, Rainer Göb |
---|---|
URN: | urn:nbn:de:bvb:20-opus-196929 |
Document Type: | Journal article |
Faculties: | Fakultät für Mathematik und Informatik / Institut für Mathematik |
Language: | English |
Parent Title (English): | Econometrics |
ISSN: | 2225-1146 |
Year of Completion: | 2019 |
Volume: | 7 |
Issue: | 3 |
Article Number: | 30 |
Source: | Econometrics (2019) 7:3, 30. https://doi.org/10.3390/econometrics7030030 |
DOI: | https://doi.org/10.3390/econometrics7030030 |
Dewey Decimal Classification: | 5 Naturwissenschaften und Mathematik / 51 Mathematik / 510 Mathematik |
Tag: | Gaussian approximation; Value at Risk; count time series; estimation error; predictive performance; quantile forecasts |
Release Date: | 2022/04/29 |
Date of first Publication: | 2019/07/06 |
Licence (German): | CC BY: Creative-Commons-Lizenz: Namensnennung 4.0 International |