Assessing out-of-sample hedging performance with commodity futures

Abstract

This thesis investigates the out-of-sample performance of minimum-variance and unconditional hedging strategies in the corn futures market from 2002 to 2019. The out-of-sample performance is captured by new measures of hedging effectiveness that are fundamentally tied to basis and net price. The findings include that optimal hedge ratios based on price changes, and the naïve hedge ratio, statistically significantly outperform all the other strategies considered. The point estimates are robust to different choices for the hedge set dates and lift dates, and regression results are robust to differing hedging horizons.