About
Bernardo Modenesi is a Ph.D. candidate in Economics, also pursuing a masters degree in Statistics, at the University of Michigan. Bernardo's interests lie in interdisciplinary statistical methods, such as network theory and machine learning, for the improvement of causal inference exercises and economic modelling. Recently, he is working on using network theory and discrete choice models to leverage information contained in linked employee-employer data for labor market modeling and also for enhancing counterfactual analysis. His past research topics include the partial identification of marginal treatment effects under the monotonicity assumption, using polynomial extrapolations. Prior to starting his Ph.D., Bernardo earned a masters degree in Economics from the Sao Paulo School of Economics (FGV-SP), where he also worked as a research assistant in econometric theory papers published in top journals. He also had previous experience working with applied econometrics in the think tank Centers for Learning on Evaluation and Results (CLEAR-FGV).
