The dynamic nature of many asset price processes andthe lack of perfect hedging assets can lead to unstable hedge ratios over time,ne- cessitating the re-estimation and rebalancing of cross-hedges. Cross- hedgingoccurs when a portfolio or asset is hedged with a statistically related yet not identical underlying derivative.Ordinary Least Squares regression is an oft applied method for estimatingconstant minimum- variance hedge ratios to curb price volatility or manage amarket-neutral porfolio. However, constant estimates are often unsuitable undercross- hedging where the dependence structure between the two assets change overtime. Rather than traditional correlation-based hedging, this paper focuses on cointegration-based cross-hedging withrespect to the equilibrium between asset prices. We apply and test theout-of-sample efficacy of models that enable the cointegrating vector, or hedgeratio between two nonstationary price series, to vary over time. Models areestimated across daily data for selected equity, bond and commodity pairs.Rolling- window regression, exponentially-weighted movingaverage and Dynamic Linear Models (Gaussian Linear State-Space Models) areinvestigated. Results show that time-varying parameter models have superiorout-of- sample hedging performance compared to constant parameter methods. Thisfinding is confirmed through extensiveMonte Carlo simulation. In practice, this reduction in basis risk comes withincurred transaction costs from routine hedge rebalancing.
展开▼
