摘要：This work deals with methodological and empirical issues related to multiperiod optimal hedging OLS estimators. We propose an analytical formula for the multiperiod minimum variance hedging ratio starting from the triangular representation of a cointegrated system DGP. Since estimating the hedge ratio matching the frequency of data with the hedging horizon leads to a sample size reduction problem, we carry out a Monte Carlo study to investigate the pattern and hedging efficiency of OLS hedging ratio based on overlapping vs non-overlapping observations exploring a range of hedging horizons and sample sizes. Finally, we applied our approach to real data for a cross hedging related to soft wheat.
