Ranking crop yield models using out-of-sample likelihood functions

• Published in: American journal of agricultural economics Vol. 86; no. 4; pp. 1032 - 1043
• Main Authors: Norwood, B, Roberts, M.C, Lusk, J.L
• Format: Journal Article
• Language: English
• Published: Malden Oxford University Press 01-11-2004; American Agricultural Economics Association; Blackwell Publishing Ltd
• Subjects: Agricultural economics; Agricultural management; Agricultural products; Agriculture; C530; Crop economics; Crop yield; Crops; Economic models; Economic theory; forecasting; Forecasting models; Forecasts; Heteroskedasticity; likelihood functions; Maximum likelihood estimation; model selection; Modeling; Probability; Probability forecasts; Q110; Risk management; Statistical variance; Studies; Yield; yield distribution; C530; risk management; forecasting; model selection; likelihood functions; Q110; yield distribution
• ISSN: 0002-9092; 1467-8276
• DOI: 10.1111/j.0002-9092.2004.00651.x

There has been considerable debate regarding which probability distribution best represents crop yields. This study ranks six yield densities based on their out-of-sample forecasting performance. The forecasting ability for each density was ranked according to its likelihood function value when observed at out-of-sample observations. Results show that a semiparametric model offered by Goodwin and Ker best forecasts county average yields.