Working Paper: NBER ID: w21466
Authors: Paul Beaudry; Patrick Feve; Alain Guay; Franck Portier
Abstract: When the VAR representation of a times series has a non-fundamental representation, standard SVAR techniques cannot be used to exactly identify the effects of structural shocks. This problem is know to potentially arise when one of the structural shocks represents news about the future. However, as we shall show, in many case the non-fundamental representation of a time series may be very close to its fundamental representation implying that standard SVAR techniques may provide a very good approximation of the effects of structural shocks even when the non-fundamentalness is formally present. This leads to the question: When is non-fundamentalness a real problem? In this paper we derive and illustrate a diagnostic based on a $R^2$ which provides a simple means of detecting whether non-fundamentalness is likely to be a quantitatively important problem in an applied settings. We use the identification of technological news shocks in US data as our running example.
Keywords: news; business cycles; nonfundamentalness; SVARs
JEL Codes: E3
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| nonfundamental representation (C59) | standard SVAR techniques cannot accurately identify effects of structural shocks (C32) |
| nonfundamental representation is close to fundamental representation (C59) | standard SVAR techniques provide good approximation of effects of structural shocks (C32) |
| R² diagnostic (C29) | detect whether nonfundamentalness is quantitatively significant (C52) |
| nonfundamentalness (D52) | affects results of SVAR analyses (C32) |
| nonfundamentalness is present (D52) | nonfundamentalness is not a serious problem in context of technological news shocks (O49) |
| significant nonfundamentalness (K19) | economic importance is minor (Q19) |
| R² value (C29) | indicates severity of nonfundamentalness problem (C62) |
| bias in recovering structural shocks (C22) | proportional to R² of projection of misspecified shocks on true shocks (C59) |