Estimation and Use of a Multivariate Parametric Model for Simulating Heteroskedastic, Correlated, Nonnormal Random Variables: The Case of Corn Belt Corn, Soybean, and Wheat Yields
开发了一个多元非正态密度函数，能分别处理偏度、峰度、异方差和变量间相关性，并用玉米带三种作物产量数据演示了其应用。
Abstract This study develops a multivariate, nonnormal density function that can accurately and separately account for skewness, kurtosis, heteroskedasticity, and the correlation among the random variables of interest. The statistical attributes of the underlying random variables and correlation processes are examined. The potential applications of this modeling tool are discussed and exemplified by analyzing and simulating Corn Belt corn, soybean, and wheat yields. While corn and soybean yields are found to be skewed and kurtotic and exhibit different variances through time, wheat yields appear normal but also heteroskedastic. A strong correlation is detected between corn and soybean yields.