Beyond Validity: SVAR Identification Through the Proxy Zoo

TL;DR

This paper tackles the challenge of identifying structural impulse responses in SVARs when researchers rely on a zoo of proxy variables that may be contaminated. It introduces generalized ranking restrictions (GRR) controlled by a proxy-quality parameter $\tau$, which bound the relative correlation of proxies with target versus non-target shocks and are combined with sign and narrative restrictions to form identified sets. The authors show that $\tau$ is partially identifiable from the joint information in the proxy zoo, derive an empirically grounded upper bound $\overline{\tau}$, and develop a suite of sensitivity tools including breakdown frontiers and proxy diagnostics. Through a simulation study and an application to US monetary policy, they demonstrate that traditional point-identified proxy-SVARs can be biased when proxies are contaminated, while their set-identified approach yields robust, informative bounds and clear guidance on the role of each proxy. The framework thus provides a transparent, computationally tractable way to assess how conclusions depend on exogeneity assumptions and the composition of the proxy zoo.

Abstract

This paper develops a framework for robust identification in SVARs when researchers face a zoo of proxy variables. Instead of imposing exact exogeneity, we introduce generalized ranking restrictions (GRR) that bound the relative correlation of each proxy with the target and non-target shocks through a continuous proxy-quality parameter. Combining GRR with standard sign and narrative restrictions, we characterize identified sets for structural impulse responses and show how to partially identify the proxy-quality parameter using the joint information contained in the proxy zoo. We further develop sensitivity and diagnostic tools that allow researchers to assess transparently how empirical conclusions depend on proxy exogeneity assumptions and the composition of the proxy zoo. A simulation study shows that proxies constructed from sign restrictions can induce biased proxy-SVAR estimates, while our approach delivers informative and robust identified sets. An application to U.S.\ monetary policy illustrates the empirical relevance and computational tractability of the framework.

Figures (13)

• Figure 1: Proxy-SVAR, Point-identified IRFs to a monetary policy shock
• Figure 2: Correlation significance map
• Figure 3: Identified sets of impulse responses under sign restrictions.
• Figure 4: Correlation significance map of sign-restricted shock
• Figure 5: Bias in Median-$B$ Proxy-SVAR Estimates

Theorems & Definitions (22)

• Example 1: Motivating proxy contamination
• Proposition 1: Generalized ranking restrictions
• Example 2: Generalized ranking with exogeneity
• Example 3: Self-sign normalization
• Example 4: Policy-sign restriction
• Example 5: Cross-variable restrictions
• Definition 1: Feasible Rotations
• Definition 2: Feasible Impulse Responses
• Proposition 2: Monotonicity
• Theorem 1: Partial Identification of Proxy Quality