Working Paper: CEPR ID: DP13948
Authors: Fabio Canova; Filippo Ferroni
Abstract: We study what happens to identified shocks and to dynamic responses when the data generating process features q disturbances but less than q variables are used in the empirical model. Identified shocks are mongrels: they are linear combinations of current and past values of all structural disturbances and do not necessarily combine disturbances of the same type. Sound restrictions may be insufficient to obtain structural dynamics. The theory used to interpret the data and the disturbances it features determine whether an empirical model is too small.An example shows the magnitude of the distortions and the steps needed to reduce them. We revisit the evidence regarding the transmission of house price and of uncertainty shocks.
Keywords: deformation; state variables; dynamic responses; structural models; house price shocks; uncertainty shocks
JEL Codes: C31; E27; E32
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| identified shocks (D80) | economic interpretation (D46) |
| fewer than q variables (C39) | identified shocks become 'mongrels' (C92) |
| identified shocks (D80) | true dynamics of structural disturbances (C69) |
| identified shocks (D80) | misleading conclusions about dynamics (C69) |
| cross-sectional deformation (C21) | identified shocks (D80) |
| time deformation (C22) | identified shocks (D80) |
| theory (B41) | choice of observables (C52) |