Good, Darrel L.

By: Isengildina-Massa, Olga; Irwin, Scott H.; Good, Darrel L.
This study uses quantile regressions to estimate historical forecast error distributions for WASDE forecasts of corn, soybean, and wheat prices, and then compute confidence limits for the forecasts based on the empirical distributions. Quantile regressions with fit errors expressed as a function of forecast lead time are consistent with theoretical forecast variance expressions while avoiding assumptions of normality and optimality. Based on out-of-sample accuracy tests over 1995/96–2006/07, quantile regression methods produced intervals consistent with the target confidence level. Overall, this study demonstrates that empirical approaches may be used to construct accurate confidence intervals for WASDE corn, soybean, and wheat price forecasts.
By: Good, Darrel L.; Irwin, Scott H.; Isengildina, Olga
This study investigates the impact of six major USDA reports in hog and cattle markets: Cattle; Cattle on Feed; Cold Storage; Hogs and Pigs; Livestock, Dairy, and Poultry Outlook (LDPO); and World Agricultural Supply and Demand Estimates (WASDE). A TARCH-in-mean model, with dummy variables to measure the impact of USDA reports and other external factors, is used to model close-to-open live-lean hog and live cattle futures returns from January 1985 through December 2004. The analysis revealed a statistically significant impact of all but Cattle and Cold Storage reports in live/lean hog futures, and all but Cold Storage reports in live cattle futures. Hogs and Pigs reports had the highest impact on live/lean hog returns by increasing conditional standard deviation 96%. Cattle, Cattle on Feed, and Hogs and Pigs reports had the highest impact on live cattle returns by increasing conditional standard deviation between 26% and 37.5%.
By: Pennings, Joost M.E.; Isengildina, Olga; Irwin, Scott H.; Good, Darrel L.
A conceptual framework is developed which provides insight into the factors affecting the impact of market advisory service (MAS) recommendations on producer pricing decisions. Data from a survey of 656 U.S. producers reveal that the perceived performance of the MAS, the way in which MAS recommendations are delivered, as well as the match between MAS and producers' marketing philosophy, are important factors explaining the impact of MAS recommendations. Risk attitude does not affect the impact of MAS recommendations on producers' decisions, suggesting producers are more interested in the price-enhancing characteristics of MAS advice than in its risk-reducing features. Key words: market advisory services, ordered probit model, producers' marketing decisions