ESTIMATING YIELD DISTRIBUTIONS WITH A STOCHASTIC TREND AND NONNORMAL ERRORS

Randomness in crop yields can be decomposed into two broad modeling fo cuses: the estimation of the mean or central tendency of the distribut ion and the dispersion around that central tendency. We propose modeli ng the central tendency of the distribution with a stochastic trend mo del and allowing for nonnormality within the stochastic trend through an inverse hyperbolic sine distribution. Results are consistent with t his construction. First, residuals around the stochastic trend model a re found to be nonnormal. Second, the inverse hyperbolic sine modifica tion of the stochastic trend model corrects both skewness and kurtosis of com yields.