A Time-Varying Gerber Statistic: Application of a Novel Correlation Metric to Commodity Price Co-Movements

This study investigates the daily co-movements in commodity prices over period 2006–2020 using a novel approach based on time-varying Gerber correlation. The statistic is computed considering set of probabilities estimated via non-traditional models that give structure to measure. results indicate there are several across commodities, these change time, and they tendentially positive. Conditional auto-regressive multithreshold logit show higher forecasting accuracy for agricultural returns, while dynamic conditional correlation more accurate energy products metals. proposed shown be superior terms power benchmark method which estimating moving rolling window.