Skip to main content
Fig. 1 | BMC Medical Research Methodology

Fig. 1

From: Does big data require a methodological change in medical research?

Fig. 1

Comparison of big data studies and controlled clinical trials. Whereas big data studies (left inset) usually benefit from the opportunistic use of existing data resources, controlled clinical trials (CCT, right inset) follow a hypothesis-driven study design that determines the type, amount and provenance of the data to be collected. The subsequent data analyses may be methodologically similar or even identical, but the results of the two study types serve rather different purposes: The outcome of a big data study, at best, is a new hypothesis that would require verification in a CCT or controlled experiment to count as ‘scientific’ (dotted arrow). A CCT, by contrast, allows validation (i.e. falsification or verification) of the initial hypothesis, potentially stimulating further studies geared at the solidification, modification or diversification of this hypothesis

Back to article page