三维平衡多水平轮换设计及其连续性估计方法研究  

Study on Three-way Balanced Multi-level Rotation Design and Successive Estimation Methods

作　　者：陈光慧[1] 刘建平[1] 

机构地区：[1]暨南大学经济学院统计学系

出　　处：《统计研究》2009年第11期100-105,共6页Statistical Research

基　　金：国家社会科学基金项目"连续性抽样调查方法及其应用研究"(08BTJ010);广东省"211工程"三期重点学科建设项目"我国政府农村统计调查制度方法改革研究"(JJ211Y006)的阶段性成果

摘　　要：针对现行多水平轮换调查存在的一系列问题,本文提出三维平衡多水平轮换模式设计及其广义组合估计方法。在这套设计方法中,将各种偏差和两类相关关系引入到广义组合估计量公式中,提高了估计量的准确性,同时在多目标调查下还应用最优化方法确定一套最优系数,使得连续性的多目标调查的整体估计精度达到最高,同时又兼顾各类目标量的精度要求。这套系统化、理论化的设计方法将为我国未来开展多水平轮换调查提供理论指导。This paper puts forward three-way balanced multi-level rotation scheme design and generalized composite estimation method which aim to solve a series of problems existing in multi-level rotation surveys. Under this method, various kinds of biases and two types of correlations are introduced into the generalized composite estimator which improves the accuracy of estimation. Meanwhile, in the successive multi-objective surveys, optimization method is applied to determine the best coefficients which not only guarantees the whole highest accuracy of sampling estimation, but also takes into account the accuracy requirements of various types of target estimators. This set of systematic and theory-based design and method would provide theoretical guidance for carrying out the multi-level rotation surveys in the future in China.

关 键 词：连续性调查 平衡多水平轮换 广义组合估计量 轮换偏差 

分 类 号：C811[社会学—统计学]