Conference Agenda

Econometrics and data science have advanced empirical methods in many important ways. Causal inference techniques continue to improve; machine learning and AI have made and will continue to expand economists’ ability to explore and evaluate causal relationships. 

But to the extent that much of our fields research has become focused on identifiable casual inference questions, is this work crowding out research that is grounded in economic theory and emphasizing public policy questions? There has been a proliferation of studies aimed at identifying the effect of X on Y but sometimes with little content on underlying mechanisms, economic or policy relevance, or reflections on the work’s value-added. Do these shifts have other implications or consequences we should be concerned about? 

Academic researchers and PhD students, of course, need novel research results for publication and for professional success. A novel dataset can offer many possibilities for causal inference testing, whereas novel topics motivated by economics and policy questions may be more challenging to develop into publishable research. 

The panelists in this session will offer their views on these fundamental and timely questions. The goal is a balanced and thoughtful exchange of perspective. Panelists will be encouraged to propose ways in which our profession can ensure that a proper balance can be achieved that maximizes the value and credibility of our discipline’s contributions.