Bayesian Hierarchical Multi-Population Mortality Modelling for China’s Provinces

Abstract

China has experienced large improvements in mortality rates, but there remain substantial variations at the provincial level. This paper develops new models to project mortality at both the national and provincial levels in China. We propose two models in a Bayesian hierarchical framework based on principal components and a random walk process, and compile a new comprehensive database containing mortality data for 31 provinces over the period 1982-2010. The baseline two-level model with a national-province hierarchy allows for information pooling across provinces, common national factors and consistency conditions. The extended three-level model with a national-region-province hierarchy pools information in the region and also allows for common factors within the region. Both models provide good estimates and reasonable forecasts for China and its provinces. The baseline two-level model provides good fit and reasonable forecasts with equal width intervals for the provinces. The three-level model has a better fit with a lower deviance information criterion and provides forecast intervals reflecting regional uncertainty. The sensitivity analyses show that the forecasts are robust when changing the trend assumptions and regional groups.

Spatial Distribution Characteristics and Influencing Factors of Intangible Cultural Heritage in the Grand Canal Cultural Belt

“…In the history of the Grand Canal Cultural Belt, a large number of immigrants moved into Luoyang in the Eastern Han Dynasty, Luoyang in the Northern Wei Dynasty, and Bianliang in the Northern Song Dynasty, which brought about cultural interaction and exchange to a certain extent. Combined with the records of the population of each region in the historical period in the "Historical Population Examination of China's Provinces and Regions" 53 and "Statistics of Households, Fields, and Fields of China Throughout the Ages" 54 , Hebei, Shandong, Henan, Jiangsu, and Zhejiang among the eight provinces (municipalities) where the Grand Canal is situated have a high percentage of the population in the historical period, which has been discussed in detail in the study of Jiao et al 43 , and the number of national ICHs of the five provinces accounted for 77% of the overall number of ICHs.…”

Multi-output Gaussian processes for multi-population longevity modelling

“…Let us also mention other methods for multi-population mortality, such as those based on hierarchical Buhlmann credibility theory (Tsai & Zhang, 2019; Tsai & Wu, 2020), hierarchical Bayes (Lu et al ., 2019) and continuous-time Levy processes (Qin & Jevtic, 2016).…”