An innovation mortality prediction model with cohort effect

Hongmin Xiao, Miaomiao Zhao, Xiang Li and Aiqin Bai

Communications in Statistics - Theory and Methods, 2024, vol. 53, issue 20, 7477-7489

Abstract: Considering that the cohort effect is added to the population mortality prediction model, the data information on the impact of birth year on mortality can be captured. In this article, the Linear Link model (LL) is extended to obtain the Extended Linear Link model (ELL) with cohort effect. Model fitting and forecasting employ a two-stage approach, first estimating the age term parameters of the extended model, and then forecasting the time parameters using an optimal combination ARIMA(p,d,q) of time series model. Using the mortality data of the Chinese population aged 0–89 from 1995 to 2018 to fit and predict the model, and to test the stability by rolling-window time frame. The results show that when the singular value decomposition method and the least square estimation method are adopted, the prediction effect of the Extended Linear Link model with cohort effect is significantly better than the previous Linear Link model, and the accuracy of fitting and predicting are improved.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2023.2264998 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:53:y:2024:i:20:p:7477-7489

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2023.2264998

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().