A0474
Title: Adaptive now- and forecasting of global temperatures under smooth structural changes
Authors: Robinson Kruse-Becher - FernUniversität in Hagen (Germany) [presenting]
Abstract: Accurate short-term now- and forecasting of global temperatures is an important issue and helpful for policy design and decision-making in the public and private sectors. A raw mixed-frequency data set is composed of weather stations around the globe (1920-2020). First, smooth variation is documented in average monthly and annual temperature series by applying a dynamic stochastic coefficient model. Second, adaptive cross-validated forecasting methods are used which are robust to smooth changes of unknown form in the short run. Therein, recent and past observations are weighted in a mean-squared error-optimal way. Overall, it turns out exponential smoothing methods (with bootstrap aggregation) often perform best. Third, by exploiting monthly data, a simple procedure is proposed to update annual nowcasts during a running calendar year and demonstrate its usefulness. Further, it is shown that these findings are robust with respect to climate zones. Finally, now- and forecasting investigates climate volatility via a range-based measure and a quantile-based climate risk measure.
