摘要：In this paper we have analyzed dynamics of milk prices in U.S. and performance of futures contracts as a tool to hedge price risk. Using spectral analysis, we find that lowering of support prices in early 1990s has induced 3-year business cycle with rising amplitude. We analyzed correlations of dairy prices and found current set of active dairy futures contracts to contain several redundant contracts. We utilized a new tool to visualize risk premium in futures prices to examine if Class III futures prices are unbiased predictors of announced USDA Class III price and we found no substantial evidence of bias. Employing partially overlapping time series model of Smith (2005) we analyzed seasonality and sources of volatility in futures prices. Model results indicate that futures prices volatility is higher in summer months, increases as time-to-maturity decreases up until eight weeks to maturity when settlement price starts to become increasingly predictable and uncertainty is quickly resolved. We name this decline in volatility in the last two trading months Inverse Samuelson effect. Further results reveal that common factor explains 50-60% of contract variance, with highest fraction of variance explained by common contract being 80+% about six to nine months prior to expiry when information regarding upper bound of dairy herd size at the time of maturity is revealed. Importance of common factor has itself pronounced seasonality that corresponds to seasonal cycles in dairy cow culling.
关键词：partially overlapping time series;spectral analysis;risk premium;futures markets;dairy policy;dairy industry
