We study the problem of measuring group differences in choices when the dimensionality of the choice set is large. We show that standard approaches suffer from a severe finite-sample bias, and we propose an estimator that applies recent advances in machine learning to address this bias. We apply...

We showed 10-second, silent video clips of unfamiliar gubernatorial debates to a group of experimental participants and asked them to predict the election outcomes. The participants' predictions explain more than 20 percent of the variation in the actual two-party vote share across the 58...

We propose a model of empirical science in which an analyst makes a report to an audience after observing some data. Agents in the audience may differ in their beliefs or objectives, and may therefore update or act differently following a given report. We contrast the proposed model with a...

We study the problem of learning about the slope of a linear relationship between an outcome (e.g., quantity) and an input (e.g., price) when the outcome is subject to time-varying, unobserved economic shocks. We show that restrictions on the absolute magnitude of the economic shocks are...

A sender sends a signal about a state to a receiver who takes an action that determines a payoff. A moderator can block some or all of the sender's signal before it reaches the receiver. When the moderator's policy is transparent to the receiver, the moderator can improve the payoff by blocking...

We study the causal interpretation of instrumental variables (IV) estimands of nonlinear, multivariate structural models with respect to rich forms of model misspecification. We focus on guaranteeing that the researcher's estimator is sharp zero consistent, meaning that the researcher concludes...