« Back to Results

JBES Session

Paper Session

Saturday, Jan. 4, 2025 10:15 AM - 12:15 PM (PST)

Hilton San Francisco Union Square, Yosemite B

Hosted By: Econometric Society

Chair: Atsushi Inoue, Vanderbilt University

Dynamic Causal Identification in a Nonlinear World: the Good, the Bad, and the Ugly

Mikkel Plagborg-Møller

Princeton University

Michal Kolesar

Princeton University

Abstract

Applied macroeconomists frequently use impulse response estimators motivated by linear models. We study whether the estimands of such procedures have a causal interpretation when the true data generating process is in fact nonlinear. We show that vector autoregressions and linear local projections onto observed shocks or proxies identify weighted averages of causal effects regardless of the extent of nonlinearities. By contrast, identification approaches that exploit heteroskedasticity or non-Gaussianity of latent shocks are highly sensitive to departures from linearity. Our analysis is based on new results on the identification of marginal treatment effects through weighted regressions, which may also be of interest to researchers outside macroeconomics.

Discussant(s)

Sílvia Gonçalves

McGill University

Edward Herbst

Federal Reserve Board

Oscar Jorda

F.R.B. of San Francisco/UC Davis

Toru Kitagawa

Brown University

JEL Classifications

C3 - Multiple or Simultaneous Equation Models; Multiple Variables