Testing for strong exogeneity in Proxy-VARs

Martin Bruns, Sascha A. Keweloh

Research output: Contribution to journalArticlepeer-review

10 Downloads (Pure)

Abstract

Proxy variables have gained widespread prominence as indispensable tools for identifying structural VAR models. Analogous to instrumental variables, proxies need to be exogenous, i.e. uncorrelated with all non-target shocks. Assessing the exogeneity of proxies has traditionally relied on economic arguments rather than statistical tests. We argue that the economic rationale underlying the construction of commonly used proxy variables aligns with a stronger form of exogeneity. Specifically, proxies are typically constructed as variables not containing any information on the expected value of non-target shocks. We show conditions under which this enhanced concept of proxy exogeneity is testable without additional identifying assumptions.
Original languageEnglish
Article number105876
JournalJournal of Econometrics
Volume245
Issue number1-2
DOIs
Publication statusPublished - Oct 2024

Keywords

  • Exogeneity test
  • Proxy VAR
  • Structural vector autoregression

Cite this