We argue that deep learning provides a promising avenue for taming the curse of dimensionality in quantitative economics. We begin by exploring the unique challenges posed by solving dynamic equilibrium models, especially the feedback loop between individual agents' decisions and the aggregate...

The observed uneven distribution of economic activity across space is influenced by variation in exogenous geographical characteristics and endogenous interactions between agents in goods and factor markets. Until recently, the theoretical literature on economic geography had focused on stylized...

Specialization is a powerful source of productivity gains, but how production networks at the industry level are related to aggregate productivity in the data is an open question. We construct a database of input-output tables covering a broad spectrum of countries and times, develop a...

We must infer what the future situation would be without our interference, and what changes will be wrought by our actions. Fortunately, or unfortunately, none of these processes is infallible, or indeed ever accurate and complete. Knight (1921)

This paper describes and applies econometric strategies for estimating regression models of economic share data outcomes where the shares may take boundary values (zero and one) with nontrivial probability. The main focus of the paper is on the conditional mean structures of such data. The paper...

This paper reviews some of the econometric methods that have been used in the economics of education. The focus is on understanding how the assumptions made to justify and implement such methods relate to the underlying economic model and the interpretation of the results. We start by...

In a labor market hierarchy, promotions are affected by the noisiness of information about the candidates. I study the hypothesis that males are more risk taking than females, and its implications for rates of promotion and abilities of survivors. I define promotion hierarchies with and without...

Dealing with endogenous regressors is a central challenge of applied research. The standard solution is to use instrumental variables that are assumed to be uncorrelated with unobservables. We instead assume (i) the correlation between the instrument and the error term has the same sign as the...