Econometrics & Applied Economics Seminar - Timo Terasvirta

Title: Long monthly temperature series and Vector Seasonal Shifting Mean and Covariance Autoregressive model

Abstract: We consider a vector version of the Shifting Seasonal Mean Autoregressive model. In this model, the seasonal means, error variances and correlations can all be time-varying. The model is used for describing dynamic behaviour of twenty long monthly European temperature series extending from the second half of the 19th century until the present decade, and contemporaneous dependence between them. The results (with some exceptions) indicate strong warming in the winter months, February excluded, and cooling followed by warming during the summer months. No clear pattern for changing correlations can be detected.