Crop‐Yield Distributions Revisited
用改进的模型和检验方法重新考察作物产量分布，发现部分产量数据非正态、有尖峰和偏斜，并探讨了使用非正态分布的好处及错误假设正态性的后果。
Abstract This article revisits the issue of crop‐yield distributions using improved model specifications, estimation, and testing procedures that address the concerns raised in recent literature, which could have invalidated previous findings of yield nonnormality. It concludes that some aggregate and farm‐level yield distributions are nonnormal, kurtotic, and right or left skewed, depending on the circumstances. The advantages of utilizing nonnormal versus normal probability distribution function models, and the consequences of incorrectly assuming crop‐yield normality are explored.