新中国政府统计调查制度的建立、发展和改革六十年

统计调查制度是统计工作的基础和规范。目前我国已建立起一个庞大的统计调查制度体系,从内容上讲,包括国民经济核算体系、统计指标体系、统计标准体系、统计调查方法体系和统计调查制度管理体系。文章首先就新中国政府统计成立60年以来我国上述五个体系的建立和发展历程进行了回顾和梳理,然后就我国政府统计调查制度的主要特点及推行中获得的有益经验进行了总结,最后指出现行统计调查制度中存在的主要问题和改革的方向。     

基于Bayes后验概率的自变量与异常点的同时识别

本文基于自变量与异常点识别隐变量的联合Bayes后验概率,给出了自变量与异常点同时识别的一般方法,且利用Gibbs抽样降低了Bayes后验概率的计算复杂度。其次,针对多值序次数据模型自变量与异常点的同时识别展开详细讨论,给出了同时识别的具体过程。最后通过模拟算例展示了本文方法的有效性。     

Determination of a new mixed variable lot-size multiple dependent state sampling plan based on the process capability index

This article proposes a new mixed variable lot-size multiple dependent state sampling plan in which the attribute sampling plan can be used in the first stage and the variables multiple dependent state sampling plan based on the process capability index will be used in the second stage for the inspection of measurable quality characteristics. The proposed mixed plan is developed for both symmetric and asymmetric fraction non conforming. The optimal plan parameters can be determined by considering the satisfaction levels of the producer and the consumer simultaneously at an acceptable quality level and a limiting quality level, respectively. The performance of the proposed plan over the mixed single sampling plan based on C_pk and the mixed variable lot size plan based on C_pk with respect to the average sample number is also investigated. Tables are constructed for easy selection of plan parameters for both symmetric and asymmetric fraction non conforming and real world examples are also given for the illustration and practical implementation of the proposed mixed variable lot-size plan.     

大数据背景下非概率抽样的统计推断问题

利用大数据进行抽样,很多情况下抽样框的构造比较困难,使得抽取的样本属于非概率样本,难以将传统的抽样推断理论应用到非概率样本中,如何解决非概率抽样的统计推断问题,是大数据背景下抽样调查面临的严重挑战。本文提出了解决非概率抽样统计推断问题的基本思路：一是抽样方法,可以考虑基于样本匹配的样本选择、链接跟踪抽样方法等,使得到的非概率样本近似于概率样本,从而可采用概率样本的统计推断理论;二是权数的构造与调整,可以考虑基于伪设计、模型和倾向得分等方法得到类似于概率样本的基础权数;三是估计,可以考虑基于伪设计、模型和贝叶斯的混合概率估计。最后,以基于样本匹配的样本选择为例探讨了具体解决方法。     

Editorial

The UK Government agencies have an interest in making greater use of administrative data. This paper discusses the methodological challenges of using administrative data held by the Department for Work and Pensions (DWP) for constructing an alternative sampling frame for the Family Resources Survey (FRS) and for replacing income data collected in the FRS. The analysis shows that administrative data would provide a good basis for sampling the FRS by linking to socio-demographic data held administratively, which would be advantageous for sampling specific sub-populations (e.g. types of benefit recipients or households with children). Sampling using administrative data also potentially offers more representative population sampling by including some addresses currently excluded from the small users Postcode Address File (PAF) but which are important to DWP, such as people living in care homes. However, comparing FRS questions and income data held administratively, suggests little overlap. Therefore, limited gains may be realised from shortening the length of the FRS by using income data from administrative sources.     

Looking for a Grandview: introducing concepts of robust sampling to policymakers and practitioners engaged in measuring the well‐being of children at the local authority level

Local authorities are increasingly required to measure and monitor the well‐being of children. One key aspect of ensuring that these data on child well‐being are robust is that they form an accurate and representative picture of that child population. Rather than being only the purview of researchers, the act of gathering outcome data now falls within the remit of policymakers and practitioners. This article therefore describes the principles and importance of solid sampling methodologies to this audience and also considers the practical reasons as to why policymakers and practitioners may require larger samples than may be necessary for a representative picture of child well‐being. These ideas are illustrated by one local authority in the UK’s approach to measuring child well‐being, using representative sampling techniques and the subsequent expansion of this sample. The consequences of expanding the sample size are illustrated by examining the impact upon key findings related to child well‐being. The potential benefits and limitations of larger samples are discussed, as are some practical solutions to the apparent impasse.     

Prevalence of classes of risk behaviors for HIV infection in a randomly selected Australian population

A random, geographically stratified sample of over 2,600 individuals aged 16 and over was interviewed in all states and territories of Australia to determine the prevalence of classes of behaviors which are associated with HIV infection. Returns from the anonymous risk behavior questionnaire (60.2% return rate) suggested that the prevalence of both male and female homosexual behavior, and contact with prostitutes, was substantially lower than that estimated by Kinsey et al. (1948, 1953). Data suggest that prevalence of classes of behaviors which place Australian individuals at risk of HIV infection may be lower than American estimates. However, the proliferation of HIV into the Australian homosexual community may be more extensive than previously assumed. The implications of these data for HIV preventive education programs and their targeting are discussed.     

Marital dissolution among the 1958 British birth cohort: The role of cohabitation

This paper investigates the effect of previous cohabitation on marital stability among the 1958 British birth cohort. Prospective data from the National Child Development Study are used to investigate the way in which family background factors and early lifecourse experiences, including cohabitation, affect the risk of first marriage dissolution by age 33. Discrete time logistic regression hazards models are used to analyse the risk of separation in the first eight years of marriage. Many socio-economic and family background factors are found to act through more intermediate determinants, such as age at marriage and the timing of childbearing, to affect the risk of separation. Previous cohabitation with another partner and premarital cohabitation are both associated with higher rates of marital breakdown. The effect of premarital cohabitation is attenuated but remains significant once the characteristics of cohabitors are controlled, and cannot be explained by the longer time spent in a partnership.     

Excitement-seeking Gambling in a Nationally Representative Sample of Recreational Gamblers

Excitement-seeking and related constructs have been associated with heavier gambling and negative health measures in problem and/or pathological gamblers. Most adults gamble recreationally and an understanding of the relationship between excitement-seeking as a motivation for gambling amongst subsyndromal gamblers has significant public health implications. Logistic regression analyses were used to examine a national sample of past-year recreational gamblers (N = 1,476) to identify characteristics distinguishing gamblers acknowledging gambling for excitement (“Excitement-seeking Gamblers” or EGs) and gamblers denying gambling for excitement (“Non-excitement-seeking Gamblers” or NEGs). EGs were more likely than NEGs to report alcohol use and abuse/dependence, any substance abuse/dependence, incarceration, large gambling wins and losses, more frequent and varied gambling, and symptoms of pathological gambling (i.e., at-risk gambling). Together, these findings indicate that EGs are more likely than NEGs to demonstrate problems in multiple areas characterized by impaired impulse control.     

事后调查的理论和它在人口普查修正中的应用

人口普查不可避免地存在误差,如遗漏、重复。为发挥普查的作用,对其结果修正是必要的。一般采用事后调查法修正。事后调查在人口普查结束后进行,主要目的是为修正提供基础数据。普查局利用这些数据,使用捕获再捕获模型,修正人口普查数。