Quantitative analysis including secondary analyses of existing data

Quantitative dissertation projects may involve analysis of an existing dataset, which is either an open-access data resource, or primary or secondary data analysis of a dataset to which your supervisor(s) may provide.  Secondary analysis of existing data involves analysing data which has been collected by someone else for some other purpose; whereas primary data has been generated by an individual (or research team) for a specific purpose. The methods of analysis could be the same for primary and secondary analyses, but the question that is being answered with secondary analyses of existing data is not what the data was specifically collated for. For example, if a team conceives of and develops a research project, collects the data to address the specific questions to be answered by the study and do their own analyses of the data it is then primary analysis. Another research team may then pose a question that could be answered through analysis of the study data – this is secondary data analysis. Secondary data analyses are often performed using routinely collected national data such as electronic health records and registry data.  Examples of research questions include:

• What are the reasons for re-admission of patients to a local hospital and to determine whether they were avoidable or not?

• What is the impact of changing out of hours GP services on attendances in A&E using local data?
  
  

Data archives exist to provide access to high quality quantitative and qualitative data from previously conducted studies and are a good source for data to undertake secondary analyses. For example UK Data Archives provides a platform to access social, economic and population data and UK Data Service access data around health, and includes studies such as the Health Survey for England and Surveys of Psychiatric Morbidity.  

• https://www.data-archive.ac.uk/

• https://ukdataservice.ac.uk/find-data/browse/ 

Other national and international repositories include:  

• Inter-university Consortium for Political and Social Research (ICPSR) maintains a data archive of research in the social and behavioural science: https://www.icpsr.umich.edu/web/pages/ 

• NHS England provides information on data and information gathered across the health and social care systems in England https://digital.nhs.uk/  

• The Demographic and Health Surveys (DHS) Program has representative data on population, health, HIV, and nutrition through more than 400 surveys in over 90 countries. https://dhsprogram.com/

• There are also sites that enable data repositories to be searched https://www.re3data.org/ 

Please be aware you will need to register and possibly request permission to access the dataset, and if you proceed you will need to agree to certain conditions.  

Useful references:

• UK Data Services: https://www.youtube.com/c/UKDATASERVICE_LIVE/videos specifically the workshop “Getting started with secondary analysis” (https://www.youtube.com/watch?v=6F_ybxy3eFs)

•  https://ukdataservice.ac.uk/learning-hub/qualitative-data/

• https://ukdataservice.ac.uk/learning-hub/survey-data/

• Boslaugh S. (2007) Secondary Data Sources for Public Health: A Practical Guide. Cambridge, Cambridge University Press.