Examining the volatility of soybean market in the MIDAS framework: The importance of bagging-based weather information

Based on the close relationship between the global soybean market and weather variables, current studies regarding soybean volatility forecasting under weather information are limited. The aim of our study is to fill this gap and examine the predictive power of soybean volatility by separately adding normal and bagging-based weather information. Methodologically, two types of extended GARCH-MIDAS approaches with weather variables, the GARCH-MIDAS-W and GARCH-MIDAS-W-MBB models, are first introduced into soybean volatility forecasting. By using the prices of soybean futures and weather information including clear-sky index, cloud cover, relative humidity, atmospheric pressure, precipitation, temperature and wind speed, our findings provide fresh evidence that predictive models that incorporate bagging-based weather information significantly outperform the models with raw weather indicators and the model without weather information. Finally, our conclusions are robust to further robustness checks. Our novel bagging-related GARCH-MIDAS-W-MBB model with weather indicators can provide fresh insights into soybean volatility forecasting.

Automated summary

Based on the relationship between the global soybean market and weather, this study aims to fill the gap in soybean volatility forecasting under weather information. By using extended GARCH-MIDAS approaches and adding weather variables, we find that models incorporating bagging-based weather information outperform those with raw weather indicators or without weather information. Our conclusions are robust to further tests, and our novel bagging-related GARCH-MIDAS-W-MBB model provides fresh insights into soybean volatility forecasting.