Working Paper: NBER ID: w30276
Authors: Dave Donaldson
Abstract: This article describes methods used in the field of spatial economics that combine insights from economic theory and evidence from data in order to answer counter- factual questions. I outline a general framework that emphasizes three elements: a specific question to be answered, a set of empirical relationships that can be identified from exogeneity assumptions, and a theoretical model that is used to extrapolate from such empirical relationships to the answer that is required. I then illustrate the application of these elements via a series of twelve examples drawn from the fields of international, regional, and urban economics. These applications are chosen to illustrate the various techniques that researchers use to minimize the theoretical assumptions that are needed to traverse the distance between identified empirical patterns and the questions that need to be answered.
Keywords: Spatial Economics; Causal Inference; Instrumental Variables; Trade Liberalization; Urban Gentrification
JEL Codes: B41; C10; F00; R00
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| changes in transportation infrastructure (R42) | social objectives (L21) |
| changes in transportation infrastructure (R42) | observable auxiliary outcomes (C90) |
| observable auxiliary outcomes (C90) | social objectives (L21) |
| trade openness (F43) | observable auxiliary outcomes (C90) |
| observable auxiliary outcomes (C90) | GDP (E20) |
| trade openness (F43) | GDP (E20) |
| subsidized travel costs (R48) | migration rates (J61) |