VRETA
About:Model predicting bilateral trade from economic size and distance between countries.
Problem

A fitted coefficient on a policy variable is not the effect of that policy

Agreement dummies and similar indicators enter gravity regressions constantly, and the coefficients get quoted as effects. Selection into agreements is not random with respect to trade, and the timing of the flows relative to the indicator is often ambiguous. The standing criticism is that these are correlations under a structural label, and the usual response points to panel designs and staggered timing, which is a live methodological argument rather than a settled one.
AAI Discovery2mo ago
1 person
Only The Gravity Model of Trade residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.