Econometrica distributed the published version of Spatial Economics for Granular Settings in March. It’s relevant for anyone working with high-dimensional data like commuting flows, trade flows, or migration flows. Our main point is that spatial models calibrated to observed flows suffer overfitting problems in granular settings. Felix Tintelnot and I diagnose the problem, show data smoothing performs better, and introduce a finite model to quantify counterfactual uncertainty.

We examine the application of quantitative spatial models to the growing body of fine spatial data used to study local economic outcomes. In granular settings in which people choose from a large set of potential residence‐workplace pairs, observed outcomes in part reflect idiosyncratic choices. Using analytical examples, Monte Carlo simulations, and event studies of neighborhood employment booms, we demonstrate that calibration procedures that equate observed shares and modeled probabilities perform very poorly in these high‐dimensional settings. Parsimonious specifications of spatial linkages deliver better counterfactual predictions. To quantify the uncertainty about counterfactual outcomes induced by the idiosyncratic component of individuals’ decisions, we introduce a quantitative spatial model with a finite number of individuals. Applying this model to Amazon’s proposed second headquarters in New York City reveals that its predicted consequences for most neighborhoods vary substantially across realizations of the individual idiosyncrasies.

The PDFs and links to replication package are available via the Econometric Society’s page and my website.