Using regression techniques to estimate hedge ratios, some results from alternative approaches

Abstract

Using data from the Sydney futures market this paper critically assesses some of the potential problems involved in the use of co integration techniques in the calculation of minimum variance hedge ratios. Firstly we use standard techniques to see how important the finding of cointegration is to the estimation of the hedge ratio More specifically we find that cointegration between spot and futures docs not imply large inefficiencies for the naive hedger using the data we consider. Secondly we consider the extent to which the stacking of the data into a time series, which effectively constrains the estimated hedge ratio to a single value over the span of the data, influences the results. If the hedge ratio differs by contract, the movement from one contract to the next is likely to lead to instability in the estimated regression coefficients. Tests for parameter instability in the estimated regression suggest that this is indeed the case and our conclusion is that it is preferable to consider the estimation of the hedge ratio in a panel setting. In such a panel setting we find that the result that the spot and futures prices are cointegrated still holds but that the estimated hedge ratios vary considerably.