Mar 20th, 2020: Lars Vilhuber

Replication and Reproducibility in Social Sciences and Statistics: Context, Concerns, and Concrete Measures

Moderated by: Tomas Dvorak
Professor of Economics at Union College


Slides from Lars's presentation. (CC-BY-NC)

Replicability is at the core of the scientific enterprise. In the past 30 years, recurring concerns about the extent of replicability (or lack thereof) of the research in various disciplines have surfaced, including in economics.

In this talk, I describe the context in which the current discussion in the social science is occurring: what are the definitions of replicability and reproducibility, what is failing, and to what extent. In particular, I discuss the concerns in economics: to what extent is this a problem in economics, what are the approaches that are being considered, and what are the possible broader implications of those approaches. Finally, I discuss the concrete measures that are being implemented under my guidance at the American Economic Association, and that are being discussed in the broader economics community.

The solutions to these problems will change the way research will be taught and conducted, in economics in particular, and in the social sciences more broadly. The implications affect undergraduate and graduate teaching, research infrastructure, and habits.

Speaker Bio

Dr. Lars Vilhuber holds a Ph.D. in Economics from Université de Montréal, Canada. He has worked in academic and government research positions, and collaborates with government and statistical agencies in Canada, the United States, and Europe. His research interests include the dynamics of the labor market. Often working with highly detailed longitudinally linked data, he has investigated the effects and causes of mass layoffs, worker mobility, and the interaction between housing and the local labor market. He has gained extensive expertise on the data needs of economists and other social scientists, having been involved in the creation and maintenance of several data systems designed with analysis, publication, replicability, and maintenance of large-scale code bases in mind. His research in statistical disclosure limitation, including through data enclaves, is a direct consequence of his interest in making data available to the broadest possible audience. His involvement in efforts to make social sciences more reproducible and transparent draws on these many diverse experiences. He is presently on the faculty of the Department of Economics at Cornell University, Executive Director of ILR’s Labor Dynamics Institute, and affiliated with the U.S. Census Bureau. He is the Data Editor of the American Economic Association, Managing Editor of the Journal of Privacy and Confidentiality, and on advisory boards of restricted-access data centers in France, Canada, and the United States.

A list of publications can be found here.