2023/07 | LEM Working Paper Series | ||||||||||||||||
![]() |
|||||||||||||||||
Identification of Vector Autoregressive Models with Nonlinear Contemporaneous Structure |
|||||||||||||||||
Francesco Cordoni, Nicolas Doremus and Alessio Moneta |
|||||||||||||||||
Keywords | |||||||||||||||||
![]() |
![]() |
||||||||||||||||
Structural VAR models; Causal Discovery; Nonlinearity; Additive Noise Models; Impulse response functions.
|
|||||||||||||||||
JEL Classifications | |||||||||||||||||
![]() |
![]() |
||||||||||||||||
C32, C52, E52
|
|||||||||||||||||
Abstract | |||||||||||||||||
![]() |
![]() |
||||||||||||||||
We propose a statistical identification procedure for structural vector autoregressive (VAR) models
that present a nonlinear dependence (at least) at the contemporaneous level. By applying and adapting
results from the literature on causal discovery with continuous additive noise models to structural
VAR analysis, we show that a large class of structural VAR models is identifiable. We spell out
these specific conditions and propose a scheme for the estimation of structural impulse response
functions in a nonlinear setting. We assess the performance of this scheme in a simulation experiment.
Finally, we apply it in a study on the effects of monetary policy on the economy.
|
Downloads
|
![]() ![]() |
|
![]()
|
![]() |