Indirect Inference Estimation of Nonlinear Dynamic General Equilibrium Models: With an Application to Asset Pricing under Skewness Risk
This paper proposes an impulse-response matching procedure designed to estimate nonlinear
dynamic models by indirect inference which uses as auxiliary model a nonlinear model based on
Mittnik (1990) The procedure is introduced through its application to a nonlinear macro-finance
model of asset pricing under skewness risk. Results show that 1) responses to productivity
shocks are asymmetric in that negative shocks induce a larger response than positive shocks,
2) skewness risk accounts about for about one-quarter of the equity risk premium, and 3) the
nonlinear model can endogenously generate conditional heteroskedasticity.