Research Statement

I’m an applied economist interested in Industrial Organization (IO). In particular, I specialize in productivity, frictions to measuring productivity, market power, and the political economy of oligopolies. I’m also interested in the intersections between IO and Labor and International Trade.

My research combines economic theory and novel methods to develop original identification strategies. A common link unifying my recent work consists of leveraging economic modeling to identify unobservables. For instance, in my JMP, I exploit the first-order conditions of firms’ cost-minimization problem to disentangle the effects of tax evasion and productivity, both unobserved. In another working paper, I take advantage of the cost function’s shape restrictions and Markov Chain Monte Carlo simulation techniques to non-parametrically test if firms behave à la Cournot, accounting for measurement error. These are examples of how my research combines economic theory with innovative techniques to provide new insights.

My unique background enables me to approach problems with an original perspective. More than ten years of experience in the manufacturing industry in areas such as procurement and supply chain gave me valuable insights into firm behavior and productivity. Furthermore, my upbringing in Latin America naturally draws me to investigate phenomena like tax evasion and media bias in concentrated markets. In brief, my cultural upbringing and former life before economics endow me with a distinct outlook.

For future work, I would like to combine machine learning with structural econometrics and economic theory. Rather than applying off-the-shelf methods developed in Computer Science, I would like to bring more economics into machine learning. The data cannot “speak for itself”; we interpret it with an underlying model. Consequently, it is better to be upfront about this model and inform the estimation methods with them, enhancing machine learning through economics.