A non-parametric panel model for climate data with seasonal and spatial variation

Jiti Gao, Oliver Linton, Bin Peng

Research output: Contribution to journalArticleResearchpeer-review


We consider a panel data model that allows for heterogeneous time trends at different locations. The model is well suited to identifying trends in climate data recorded at multiple stations. We propose a new estimation method for the model and derive an asymptotic theory for the proposed estimation method. For inferential purposes, we develop a bootstrap method for the case where weak correlation presents in both dimensions of the error terms. We examine the finite-sample properties of the proposed model and estimation method through extensive simulated studies. Finally, we use the newly proposed model and method to investigate monthly rainfall, temperature, and sunshine data of the UK, respectively. Overall, we find spring and winter have changed significantly over the past 50 years. Changes vary with respect to locations for the other seasons.

Original languageEnglish
Pages (from-to)158-177
Number of pages20
JournalJournal of the Royal Statistical Society Series A-Statistics in Society
Issue number1
Publication statusPublished - Jan 2024


  • climate data
  • panel model
  • seasonal and spatial variation
  • bootstrap

Cite this