Data-Driven vs. Hypothesis-Driven Research: Making sense of big data
Willy C. Shih, Sen H. Chai · Academy of Management Proceedings · 2016
With the availability of large datasets and advanced correlation/statistical methods, will we still need to rely on hypotheses in scientific inquiry? Traditionalists argue that in purely data-driven methods, one may not know where to look for those interesting findings if no hypotheses were formed beforehand. Big data advocates, on the other hand, argue that with no prior beliefs, one is not constrained by established ways of thinking or doing, opening the possibilities of breakthrough insights where nobody had looked before. To explore these questions, we examine several fields and describe an historical progression in knowledge production. We believe that in these contexts large scale data collection and analysis represent the next step - going beyond the capabilities of todays simulation models with an empirical data-collection driven approach.