BRINGING SOCIETY BACK IN SURVEY RESEARCH AND MACRO-METHODOLOGY
BRINGING SOCIETY BACK IN SURVEY RESEARCH AND MACRO-METHODOLOGY
复制标题
DOI：
10.1177/000276426801200201
复制
发表时间：
1968-01-01
影响因子：
3.2
通讯作者：
BARTON, AH
中科院分区：
文献类型：
--
作者：
BARTON, AH
在过去的三十年里，实证性的社会研究一直以抽样调查为主。但就像往常一样，通过对个人进行随机抽样，这项调查是一个社会学的绞肉机，将个人从他的社会背景中剥离出来，并保证研究中没有人与其中的其他任何人互动。这有点像生物学家把他的实验动物放进汉堡机，用显微镜观察每一个百分之一的细胞；解剖学和生理学消失了，结构和功能消失了，只剩下细胞生物学了。如果我们想准确地描述大量人口的个体特征，抽样调查比人口普查效率高得惊人。但是，产生最准确的描述性统计数据的样本设计与解释态度和行为、追踪刺激对人群的影响或分析社会制度运行所需的样本设计之间存在内在矛盾。一个好的描述性调查试图减少抽样误差。在抽样误差的计算公式中，有两个主要变量：总样本量和聚类修正。为了尽可能地减少抽样误差，我们必须尽可能地分散采访。实际上，为了节省出行时间，采访几乎总是聚在一起；但这被认为是对理想的令人遗憾的妥协，在分析中，聚在一起并不起作用。如果我们的目标是了解人们的行为，而不是简单地记录下来，我们想知道主要的群体、社区、组织、社交圈和社区；关于互动、沟通、角色期望和社会控制。我们想要家庭集群，邻里集群，友谊集群，工作小组集群；我们想要社会测量样本。有时有一些巧妙的方法可以同时获得良好的描述性统计数据和关于
ALLEN H. BARTON m For the last thirty years, empirical social research has been dominated by the sample survey. But as usually practiced, using random sampling of individuals, the survey is a sociological meatgrinder, tearing the individual from his social context and guaranteeing that nobody in the study interacts with anyone else in it. It is a little like a biologist putting his experimental animals through a hamburger machine and looking at every hundredth cell through a microscope; anatomy and physiology get lost, structure and function disappear, and one is left with cell biology. If we want to describe accurately the individual characteristics of a large population, the sample survey is miraculously efficient compared with a census. But there is an inherent contradiction between the sample design which produces the most accurate descriptive statistics and that which is needed to explain attitudes and behavior, trace the effects of stimuli on a population, or analyze the operation of a social system. A good descriptive survey tries to reduce sampling error. In the formula for computing sampling error there are two major variables: the total sample size and the correction for clustering. To reduce the sampling error as much as possible, we must scatter the interviews as much as possible. In practice, interviews are almost always clustered, to save travel time; but this is regarded as a regrettable compromise of the ideal, and in the analysis the clusters play no part.If our aim is to understand people’s behavior rather than simply to record it, we want to know about primary groups, neighborhoods, organizations, social circles, and communities; about interaction, communication, role expectations, and social control. We would like family clusters, neighborhood clusters, friendship clusters, work group clusters; we would like sociometric samples. There are sometimes ingenious ways of getting both good descriptive statistics and information on