Working Paper: CEPR ID: DP2333
Authors: Fabio Canova; Joaquim Pires Pina
Abstract: We examine the effects of extracting monetary policy disturbances with semi-structural and structural VARs, using data generated by a limited participation model under partial accommodative and feedback rules. We find that, in general, misspecification is substantial: short run coefficients often have wrong signs; impulse responses and variance decompositions give misleading representations of the dynamics. Explanations for the results and suggestions for macroeconomic practice are provided.
Keywords: general equilibrium; monetary policy; identification; structural VARs
JEL Codes: C32; C68; E32; E52
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| monetary policy disturbances (E39) | structural VAR representation (C32) |
| inertial restrictions (D10) | poor representation of dynamics (C69) |
| estimated short-run coefficients (C51) | misrepresentation of true dynamics (C69) |
| policy rules and identification schemes (E61) | variation in impulse responses (C22) |
| variance decomposition (C29) | underestimation of monetary policy shocks (E39) |
| exclusion restrictions (C24) | biased coefficient estimates (C51) |
| structural VAR models (C32) | inadequate capture of real data dynamics (C69) |