4.2 Data analysis: qualitative, quantitative and mixed methods
Analysing data is always an artificial but necessary simplification of a much more complex reality. Our research design defines the limits of our investigation. Consequently, a good analysis is at best a tentative explanation rather than a definitive answer to our research questions.
In the data pipeline, analysis follows collection and precedes interpretation. Together, these are the three main components of what we call research methods. Generally, starting from data is a bad principle. The research questions and objectives should determine our research methods. We should seek answers to our research questions through data rather than looking for research questions in data. This is why it is so important to have a research design that guides our methods. Following a traditional division, research designs are ‘types of inquiry within qualitative, quantitative, and mixed methods approaches that provide specific direction for procedures in a research’ (Creswell, 2013). Although there has been an effort of methodological dialogue and convergence, the research practice shows that most scientific production falls neatly on either the qualitative or the quantitative side.