小域估计方法在小品种农作物播种面积统计中的应用

An Application of Small Area Estimation on Planted Area Statistics for Rare Crops

我国以省级目标总体开展的现行农产量抽样调查,着眼于农作物主要品种的省级推算,而小品种农作物的总体分布呈偏态,往往有效样本量相对不足,不能解决小品种农作物播种面积的推算问题,同时对分县的主要品种农作物播种面积进行的直接推算也不能满足精度要求。现阶段对小品种农作物播种面积的统计方法成为农村统计方法制度改革迫切需要研究的课题之一。本文选择了河北省张家口的蔚县,利用小域估计方法对小品种农作物播种面积进行了统计推断,从推断结果看,得到了比较好的估计精度。利用蔚县实际数据为总体进行的抽样仿真分析,从实证角度阐述了小域估计方法对这一问题的有效性,而且分析结果也表明该方法可以显著提高估计效果。

China＇s current agricultural crop surveys aimed at a provincial level planted area estimation for major crops. Currently,there is short of a solution to estimate planted area for rare crops for the lack of adequate samples due to their skewed distributions. At the same time,it is also difficult to obtain a precise county level estimation in terms of variation for the major crops based on direct expansion. It is becoming an imminent demand of the methodological study on estimation of planted area for rare crops in agricultural statistics. This paper applies the method of small area estimation to obtain more precise estimates on rare crops in the context of a pilot study of Yu Xian county in the Hebei province. Simulation studies were conducted by analyzing sampled villages from the real data of Yu Xian county as the sampling frame. It is illustrated that the method we used has improved the planted area estimation for rare crops from the angle of empirical perspective.