Ranking Crop Yield Models Using Out-of-Sample Likelihood Functions

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 <link rid="b5">Goodwin and Ker</link> best forecasts county average yields. Copyright 2004 American Agricultural Economics Association.