Teaching datasets and workshops based on the British Cohort Studies
In December 2007 CLS completed a two-year project which aimed to create a set of teaching datasets and associated resources for lecturers in higher education. These are based on the 1958 National Child Development Study, the 1970 British Cohort Study and the Millennium Cohort Study. The project was funded under the ESRC Researcher Development Initiative (RDI).
About the datasets
Our aim was to provide a series of datasets that contain fully cleaned and documented subsets of the variables from these important longitudinal data resources. The datasets facilitate teaching of quantitative data analysis, in particular teaching longitudinal analysis to postgraduate and undergraduate students. The datasets are also of value to the wider research community as they include many of the most commonly used variables from the studies, such as data on qualifications, social class, marital status, income, number and ages of children, etc.
The project was co-ordinated by Jane Elliott and Ian Plewis. The research officer was Samantha Parsons.
Teaching resources currently available
The fully cleaned and documented subsets of variables from these important longitudinal data resources are available from the ESRC data archive. The documentation that accompanies the datasets is available on this page. The first set of resources is based on the Malaise Inventory, an established scale to measure signs of psychological distress or depression in teenagers or adults. Cohort members in both NCDS and BCS70 have completed the Malaise Inventory at various ages from age 16. A supplementary resource based on BCS70 cohort members' mothers' responses to the Malaise Inventory is also available. The second set of resources is based on the Rutter Behaviour Scale, again, an established scale to measure signs of behaviour disorders in children that cohort members' parents in both NCDS and BCS70 have completed at various ages in childhood. The final set of resources documents 'key variables' or rather many of the most commonly used variables from the two studies, such as data on qualifications, social class, marital status, income, number and ages of children etc.
You can also download from the links on this page two Reading Lists. The first list has details of books and other useful resources about Event history data, Survival Analysis and Cox Proportional Hazard Models. The second list has details of books about Quantitative analysis in general, Research Design and Longitudinal Research.
A series of workshops to publicise and support the use of the teaching datasets and associated resources were held in 2006 and 2007. Materials from the workshops such as Powerpoint slides are available from CLS.
Register your interest
To find out more about this project and the teaching resources available from CLS, please e-mail Sam Parsons at firstname.lastname@example.org.