Methodological Advancements on the use of Administrative Data in Official Statistics

国家统计局正在将资源用于推动在官方统计系统中使用行政数据。这是英国国家统计局(ONS)的首要任务，因为他们正在经历统计系统的转型，以便在未来的人口普查和人口统计中更多地使用行政数据。行政数据被定义为次要数据来源，因为它们是由其他机构根据与组织、公共行政部门和政府机构的行政程序有关的事件或交易而产生的。然而，它们有可能成为编制官方统计数据的重要数据来源，因为它们大大降低了答复的成本和负担，并提高了这类系统的效率。在统计系统中嵌入行政数据并不是没有代价的，了解可能出现错误的潜在位置是至关重要的。行政数据总误差框架列出了将行政数据用作统计数据时所有可能的错误来源，具体取决于它是单一数据源还是与其他数据源(如调查数据)相结合。对于单一的行政数据，误差的主要来源之一是对感兴趣的目标人群的覆盖和表示。当随着时间的推移提供管理数据时，这一点尤其重要，例如用于维护商业登记簿的税务数据。对于本研究项目的子项目1，我们制定了质量指标，使统计机构能够评估行政数据是否对目标人群具有代表性，以及哪些子组可能缺失或复盖过多。这对于从行政数据中产生无偏见的估计是至关重要的。统计机构的另一个优先事项是从多个行政和调查数据来源编制人口特征估计的统计登记册，例如就业统计数据。使用行政数据建立脊椎，调查数据可以在一组常见匹配变量上使用记录链接和统计匹配方法进行整合。这将是分项目2的主题，分成几个研究主题。第一个主题是增加统计预测和关联结构是否会改善链接和数据集成。第二个主题是研究一种大规模推算框架，用于推算统计寄存器中丢失的目标变量，其中丢失的数据可能是由于多种潜在机制造成的。因此，第三个专题将致力于改进大规模归责框架，以减少可能的计量误差，例如通过在方法中增加基准和其他限制。完成统计登记后，就可以很容易地汇总当地关键目标变量的估计数。但是，还必须通过均方误差来衡量这些估计的精度，这将是分项目的第四个专题。最后，将这种产生官方统计数据的新方法与通过调查权重和基于模型的估计方法纳入行政数据的更常见的方法进行了比较。换句话说，我们评估‘衡量’或‘归因于’人口特征估计--这是调查统计学家在过去十年研究的一个关键问题--哪个更好。

National Statistical Institutes (NSIs) are directing resources into advancing the use of administrative data in official statistics systems. This is a top priority for the UK Office for National Statistics (ONS) as they are undergoing transformations in their statistical systems to make more use of administrative data for future censuses and population statistics. Administrative data are defined as secondary data sources since they are produced by other agencies as a result of an event or a transaction relating to administrative procedures of organisations, public administrations and government agencies. Nevertheless, they have the potential to become important data sources for the production of official statistics by significantly reducing the cost and burden of response and improving the efficiency of such systems. Embedding administrative data in statistical systems is not without costs and it is vital to understand where potential errors may arise. The Total Administrative Data Error Framework sets out all possible sources of error when using administrative data as statistical data, depending on whether it is a single data source or integrated with other data sources such as survey data. For a single administrative data, one of the main sources of error is coverage and representation to the target population of interest. This is particularly relevant when administrative data is delivered over time, such as tax data for maintaining the Business Register. For sub-project 1 of this research project, we develop quality indicators that allow the statistical agency to assess if the administrative data is representative to the target population and which sub-groups may be missing or over-covered. This is essential for producing unbiased estimates from administrative data. Another priority at statistical agencies is to produce a statistical register for population characteristic estimates, such as employment statistics, from multiple sources of administrative and survey data. Using administrative data to build a spine, survey data can be integrated using record linkage and statistical matching approaches on a set of common matching variables. This will be the topic for sub-project 2, which will be split into several topics of research. The first topic is whether adding statistical predictions and correlation structures improves the linkage and data integration. The second topic is to research a mass imputation framework for imputing missing target variables in the statistical register where the missing data may be due to multiple underlying mechanisms. Therefore, the third topic will aim to improve the mass imputation framework to mitigate against possible measurement errors, for example by adding benchmarks and other constraints into the approaches. On completion of a statistical register, estimates for key target variables at local areas can easily be aggregated. However, it is essential to also measure the precision of these estimates through mean square errors and this will be the fourth topic of the sub-project. Finally, this new way of producing official statistics is compared to the more common method of incorporating administrative data through survey weights and model-based estimation approaches. In other words, we evaluate whether it is better 'to weight' or 'to impute' for population characteristic estimates - a key question under investigation by survey statisticians in the last decade.