出版社：Society for Longitudinal and Life Course Studies
摘要：The most recent UK birth cohort study, known as ‘Life Study’ was a longitudinal study planned to involve some 80,000 babies and comprised two components. The largest, the ‘Pregnancy Component’ was to consist of around 60,000 pregnant women who were to be recruited when attending for a routine antenatal ultrasound at selected maternity units in England. The other component, the ‘Birth Component’ was to be a random sample of intended size 20,000 live births across the UK. Recruitment to the cohort was to take place over a period of four years starting in 2015. Innovative sampling procedures had been designed and tested and a synthetic dataset produced with similar characteristics to the anticipated survey data was produced to study the performance of the sampling procedures and explore analysis strategies. This research note describes the proposed sample design, and discusses how the two components were to be integrated to provide a consistent dataset for users. Approaches to the provision of suitable sampling weights and modelling approaches are also presented. Lessons are drawn for designs of future cohort studies.
其他摘要：The most recent UK birth cohort study, known as ‘Life Study’ was a longitudinal study planned to involve some 80,000 babies and comprised two components. The largest, the ‘Pregnancy Component’ was to consist of around 60,000 pregnant women who were to be recruited when attending for a routine antenatal ultrasound at selected maternity units in England. The other component, the ‘Birth Component’ was to be a random sample of intended size 20,000 live births across the UK. Recruitment to the cohort was to take place over a period of four years starting in 2015. Innovative sampling procedures had been designed and tested and a synthetic dataset produced with similar characteristics to the anticipated survey data was produced to study the performance of the sampling procedures and explore analysis strategies. This research note describes the proposed sample design, and discusses how the two components were to be integrated to provide a consistent dataset for users. Approaches to the provision of suitable sampling weights and modelling approaches are also presented. Lessons are drawn for designs of future cohort studies.
