Approximating Time Varying Structural Models with Time Invariant Structures

Working Paper: CEPR ID: DP10803

Authors: Fabio Canova; Filippo Ferroni; Christian Matthes

Abstract: The paper studies how parameter variation affects the decision rules of a DSGE model and structural inference. We provide diagnostics to detect parameter variations and to ascertain whether they are exogenous or endogenous. Identification and inferential distortions when a constant parameter model is incorrectly assumed are examined. Likelihood and VAR-based estimates of the structural dynamics when parameter variations are neglected are compared. Time variations in the financial frictions of a Gertler and Karadi's (2010) model are studied.

Keywords: endogenous variations; misspecification; structural model; time varying coefficients

JEL Codes: C10; E27; E32


Causal Claims Network Graph

Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.


Causal Claims

CauseEffect
exogenous parameter variations (C51)unchanged structural dynamics (C69)
endogenous parameter variations (C51)altered structural dynamics (C69)
neglecting endogenous parameter variations (C51)significant biases in parameter estimates (C51)
neglecting endogenous parameter variations (C51)mischaracterization of structural dynamics (C69)
endogenous parameter variations (C51)incorrect welfare cost comparisons (D69)
endogenous parameter variations (C51)distorted estimates (C51)
time-invariant models (C32)deteriorating performance when substantial parameter variations occur (D29)

Back to index