I have worked with a number of datasets which were routinely collected rather than specifically designed for a research project. [1, 2, 3]
 Y-F Chen, A J Avery, K E Neil, C Johnson, M E Dewey, and I H Stockley. Incidence and possible causes of prescribing potentially hazardous/contraindicated drug combinations in general practice. Drug Safety, 28:67–80, 2005.
 A N Siriwardena, P Fairchild, S Gibson, T Sach, and M E Dewey. Investigation of the effect of a countrywide protected learning time scheme on prescribing rates of ramipril: interrupted time series study. Family Practice, 24:26–33, 2007.