Comparing long monthly Chinese and selected European temperature series using the Vector Seasonal Shifting Mean and Covariance Autoregressive model

Publikation: Working paperForskning


  • rp19_19

    Forlagets udgivne version, 1,81 MB, PDF-dokument

  • Changli He, Tianjin University of Finance and Economics, Kina
  • Jian Kang, Tianjin University of Finance and Economics, The Hong Kong Polytechnic University, Kina
  • Timo Teräsvirta
  • Shuhua Zhang, Tianjin University of Finance and Economics, Kina
The purpose of this paper is to study differences in long monthly Asian and European temperature series. The longest available Asian series are those of Beijing and Shanghai, and they are compared with the ones for St Petersburg, Dublin and Uccle that have a rather different climate. The comparison is carried out in the Vector Shifting Mean and Covariance Autoregressive model that the authors have previously used to analysed 20 long European temperature series. This model gives information about mean shifts in these five temperature series as well as (error) correlations between them. The results suggest, among other things, that warming has begun later in China than in Europe, but that the change in the summer months in both Beijing and Shanghai has been quite rapid.
UdgiverInstitut for Økonomi, Aarhus Universitet
Antal sider34
StatusUdgivet - 4 nov. 2019
SerietitelCREATES Research Papers


  • Climate change, Changing seasonality, Long monthly Chinese temperature series, Nonlinear model, Nonlinear time series, Time-varying correlation, Time-varying variance, Time-varying vector smooth transition autoregression

Se relationer på Aarhus Universitet Citationsformater


Ingen data tilgængelig

ID: 170588466