A0850
Title: Local projections inference (preliminary version)
Authors: Lola Gadea - University of Zaragoza (Spain) [presenting]
Abstract: Although the proposal of semiparametric estimation of impulse-response functions by local projections has aroused great interest in the literature, the procedures proposed are not entirely satisfactory. These bootstrap procedures typically rely on assuming that the data generating process (DGP) is a finite order vector autoregression (VAR), often taken to be that implied by the local projection at horizon 1. Although a convenient approximation, the precise form of the parametric model generating the data is assumed to be unknown, in keeping with the logic behind local projections. However, it is assumed that the model belongs to a broad class. Specifically, if one is willing to assume that the DGP is perhaps an infinite order process, a larger class of models can be accommodated, and more tailored bootstrap procedures can be constructed. This approach opens the door to all kinds of empirical applications to analyse causal effects in both the short and long term without being locked into a particular model.