Search

The prices of cash crops are crucial to the livelihood of millions of households in developing countries. While the influence of financial investors on the determination of global commodity prices on derivative exchanges is extensively discussed, the role of physical actors in the global value chains (GVCs) is largely disregarded in the 'financialization of commodities' debate. This excludes, however, the interlinked activities of GCV lead firms in financial and physical commodity markets, by which prices are transmitted to producer countries. We, therefore, relate the buying and pricing strategies of lead firms in the coffee, cocoa and cotton GVCs with their activities as hedgers on commodity derivatives markets. Based on Open Interest (OI) data in the Commitments of Traders (COT) database, a measure of buying and selling pressure by trader categories is applied in a GARCH model. Our findings show that liquidity provision by hedgers allows speculators' position takings to drive returns of global benchmark prices. We identify elaborated financial hedging and physical price-setting strategies as a determinant of hedgers' activities on derivative markets, which contributes to price transmission through GVCs and thereby expose smallholder and other actors in cash crops in producer countries to price risks.

We explore the benefits of forecast combinations based on forecast-encompassing tests compared to simple averages and to Bates–Granger combinations. We also consider a new combination algorithm that fuses test-based and Bates–Granger weighting. For a realistic simulation design, we generate multivariate time series samples from a macroeconomic DSGE-VAR (dynamic stochastic general equilibrium–vector autoregressive) model. Results generally support Bates–Granger over uniform weighting, whereas benefits of test-based weights depend on the sample size and on the prediction horizon. In a corresponding application to real-world data, simple averaging performs best. Uniform averages may be the weighting scheme that is most robust to empirically observed irregularities.

We explore the benefits of forecast combinations based on forecast- encompassing tests compared to simple averages and to Bates-Granger combinations. We also consider a new combination method that fuses test-based and Bates-Granger weighting. For a realistic simulation design, we generate multivariate time-series samples from a macroe- conomic DSGE-VAR model. Results generally support Bates-Granger over uniform weighting, whereas benefits of test-based weights depend on the sample size and on the prediction horizon. In a corresponding application to real-world data, simple averaging performs best. Uni- form averages may be the weighting scheme that is most robust to empirically observed irregularities.

We study the benefits of forecast combinations based on forecast-encompassing tests relative to uniformly weighted forecast averages across rival models. For a realistic simulation design, we generate multivariate time-series samples of size 40 to 200 from a macroeconomic DSGE-VAR model. Constituent forecasts of the combinations are formed from four linear autoregressive specifications, one of them a more sophisticated factor-augmented vector autoregression (FAVAR). The forecaster is assumed not to know the true data-generating model. Results depend on the prediction horizon. While one-step prediction fails to support test-based combinations at all sample sizes, the test-based procedure clearly dominates at prediction horizons greater than two.

We use data generated by a macroeconomic DSGE model to study the relative benefits of forecast combinations based on forecast-encompassing tests relative to simple uniformly weighted forecast averages across rival models. Assumed rival models are four linear autoregressive specifications, one of them a more sophisticated factor-augmented vector autoregression (FAVAR). The forecaster is assumed not to know the true data-generating DSGE model. The results critically depend on the prediction horizon. While one-step prediction hardly supports test-based combinations, the test-based procedure attains a clear lead at prediction horizons greater than two.