Empirical Confidence Intervals for WASDE Forecasts of Corn, Soybean, and Wheat Prices

Marketing and Outlook Research Report 2009-01

74 Pages Posted: 15 Oct 2009

See all articles by Olga Isengildina Massa

Olga Isengildina Massa

Virginia Polytechnic Institute and State University

Darrel L. Good

University of Illinois at Urbana-Champaign - Department of Agricultural and Consumer Economics

Scott H. Irwin

University of Illinois at Urbana-Champaign

Date Written: January 15, 2009

Abstract

This study investigates empirical methods of generating prediction intervals for WASDE forecasts of corn, soybean, and wheat prices over the 1980/81 through 2006/07 marketing years. Empirical methods use historical forecast errors to estimate forecast error distributions, which are then used to predict confidence limits of forecasts. Five procedures were used to estimate empirical confidence limits, including histograms, kernel density estimation, logistic distribution, quantile regression, and quantile regression with stocks-to-use ratios. The procedures were compared based on out-of-sample performance, where the first 15 observations (1980/81-1994/95) were used to generate confidence limits for the 16th year (1995/96); the first 16 observations were used to generate confidence limits for the 17th year (1996/97) and so on. Based on the results of accuracy tests for empirical confidence intervals over 1995/96 through 2006/07, all five empirical procedures included in this study generated confidence intervals that were not significantly different from the target confidence levels (80% pre-harvest and 90% post harvest). When monthly hit rates were averaged pre- and post-harvest across all three commodities, the kernel density-based method appears most accurate prior to harvest with an average hit rate of 82%, followed by the logistic distribution (76%), quantile regression-based methods (71-72%), and histogram (71%). After harvest, the kernel density-based method and the quantile regression-based method were the most accurate with average hit rates of 95%, followed by the logistic distribution based methods (92%), the histogram-based methods (89%), and the quantile regression methods with stocks/use ratio (88%). Overall, this study demonstrates that empirical approaches may be used to construct more accurate confidence intervals for WASDE corn, soybean, and wheat price forecasts.

Keywords: forecast, USDA, commodity, confidence interval, empirical

JEL Classification: Q11, Q13

Suggested Citation

Isengildina Massa, Olga and Good, Darrel L. and Irwin, Scott, Empirical Confidence Intervals for WASDE Forecasts of Corn, Soybean, and Wheat Prices (January 15, 2009). Marketing and Outlook Research Report 2009-01, Available at SSRN: https://ssrn.com/abstract=1392388 or http://dx.doi.org/10.2139/ssrn.1392388

Olga Isengildina Massa (Contact Author)

Virginia Polytechnic Institute and State University ( email )

250 Drillfield Drive
231-A Hutcheson Hall
Blacksburg, VA 24061
United States
24061 (Fax)

HOME PAGE: http://https://aaec.vt.edu/people/faculty/Isengildina_Olga.html

Darrel L. Good

University of Illinois at Urbana-Champaign - Department of Agricultural and Consumer Economics ( email )

1301 W. Gregory Drive
326 Mumford Hall, MC-710
Urbana, IL 61801
United States

Scott Irwin

University of Illinois at Urbana-Champaign ( email )

344 Mumford Hall
1301 W. Gregory Dr.
Urbana, IL 61801
United States
217-333-6087 (Phone)

HOME PAGE: http://https://scotthirwin.com/

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
82
Abstract Views
971
rank
337,160
PlumX Metrics