Disentangling the importance of individual, family and neighbourhood factors on educational outcomes using sibling data

人们出生的家庭对个人的生活结果有很大的影响，包括教育和职业结果。分析教育成果中的社会不平等现象的工作很多，但这项研究的大部分依赖于个人调查数据，这些数据只包含关于原籍家庭的有限信息，没有或仅包含关于他们所居住地区的信息。这项工作很可能低估了原籍家庭对年轻人教育的重要程度，因为许多家庭特征没有被观察到，可能会混淆家庭和邻居的影响。这项博士项目将采用兄弟姐妹设计，以区分个人因素(例如性别、年龄、族裔)、共同家庭因素(包括兄弟姐妹在出生和成长过程中共有的所有可测量和不可测量的特征)和环境因素(家庭居住地的特征)对年轻人教育成果的影响。该项目将开发一个新的、独特的兄弟姐妹数据集，该数据集将来自三个行政数据源(苏格兰纵向研究、重大事件出生数据和ScotXed数据)的信息联系起来，并包含关于考试结果和学校课程选择以及地理流动性的纵向信息。这项研究将需要使用先进的统计方法，即纵向数据分析和多层次空间数据分析的最新发展。它还需要了解如何处理来自行政来源的敏感和复杂的相关数据。学生将接受有关数据安全和处理敏感数据的不同方面的培训。博士学位将为学生提供一个绝佳的机会来使用独特的数据集，获得先进的统计技能，并向政策制定者和学校实践者提供有影响力的研究成果。学生将加入教育中的高级定量研究中心的一个充满活力的定量社会科学家社区，并有机会获得通过Q-Step中心、研究培训中心和爱丁堡大学统计中心提供的培训，以及由ESRC国家研究方法中心提供的培训。

The family in which people are born has a strong influence on individual life outcomes, including educational and occupational outcomes. There is a voluminous body of work analysing social inequalities in educational outcomes but most of this research relies on individual survey data which contain only limited information about the family of origin and no or limited information about the areas where they live. This work is likely to underestimate the full extent to which family of origin matters for young people's education since many family characteristics are unobserved and they may confound the effect of family and neighbourhood.This PhD project will adopt a sibling design to disentangle the effects of individual factors (e.g. gender, age, ethnicity), shared family factors (including all measured and unmeasured characteristics shared by siblings at birth and during their upbringing) and contextual factors (characteristics of the family's area of residence) on young people's educational outcomes. The project will exploit a new, unique sibling data set which links information from three administrative data sources (the Scottish Longitudinal Study, Vital Events birth data and ScotXed data) and contains longitudinal information on exam results and school curriculum choices as well as geographical mobility. The study will require the use of advanced statistical methods, i.e. longitudinal data analysis and the latest developments in multilevel spatial data analysis. It will also require an understanding of how to work with sensitive and complex linked data from administrative sources. The student will receive training on data security and different aspects of working with sensitive data. The PhD will provide an excellent opportunity for the student to work with a unique data set, to acquire advanced statistical skills and to produce and present impactful research to policy makers and school practitioners. The student will join a vibrant community of quantitative social scientists in the Advanced Quantitative Research in Education Hub and have access to training provided through the Q-Step centre, the Research Training Centre and the Centre for Statistics in the University of Edinburgh, as well as training provided by the ESRC National Centre for Research Methods.