抽样调查基础理论体系研究综述与应用  

The Review and Application of Basic Theoretical System about Sampling Survey

作　　者：陈光慧[1] 刘建平[1] 

机构地区：[1]暨南大学经济学院,广东广州510632

出　　处：《数理统计与管理》2015年第2期284-296,共13页Journal of Applied Statistics and Management

基　　金：国家社会科学基金青年项目(14CTJ014);全国统计科学研究计划项目(2012LY014);中央高校基本科研业务费专项资金(暨南启明星计划)项目(12JNQM006)

摘　　要：针对抽样调查中抽样设计、估计量设计及方差估计等方面存在的关键理论性问题,运用数理统计方法,从抽样调查的两个主要环节,即抽样设计和抽样估计环节进行基础理论的综述研究,以S(a|¨)rndal et al.(1992)等成果中研究的抽样设计、示性变量、包含概率、π估计量等核心概念为基础,并引入超总体模型这一研究工具进行模型辅助估计,最终归纳整理出一套现代抽样调查的基础理论体系,为后续更好地开展抽样调查基础理论和应用研究奠定方法论基础。这套基础理论体系具有开阔性、统一性和易于推广性等一系列优势,对于抽样调查从设计到估计的全过程起着基础性作用。This paper considers the key theoretical issues from sampling survey,such as sampling design,estimator design and variance estimation,uses the mathematical statistical methods,and carries out the basic theoretical research and review from the two main parts of sampling survey,sampling design and sampling estimation.The core concepts and tools are based on Sarndal et al.（1992）,including sampling design,the indicative variables,including probability,the π estimator.The superpopulation model as a research tool is introduced further,then,model-assisted estimation methods are used from constructing various types of superpopulation regression models.Ultimately,the theoretical system about modern sampling survey is summarized which lays the methodological basis to better carry out the following basic theory and applied researches about sampling survey.This set of basic theoretical system has a series of advantages,such as the open-minded,uniformity and easy promotion,and plays a fundamental role in the whole survey process from design to estimation.

关 键 词：抽样调查 抽样设计 包含概率 超总体回归模型 广义回归估计量 

分 类 号：C811[社会学—统计学] O212[理学—概率论与数理统计]