Working Paper: CEPR ID: DP9692
Authors: A. Ronald Gallant; Raffaella Giacomini; Giuseppe Ragusa
Abstract: The contribution of generalized method of moments (Hansen and Singleton, 1982) was to allow frequentist inference regarding the parameters of a nonlinear structural model without having to solve the model. Provided there were no latent variables. The contribution of this paper is the same. With latent variables.
Keywords: Particle Filter; Structural Models
JEL Codes: C32; C36; E27
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
Cause | Effect |
---|---|
GMM estimator (C51) | consistent and asymptotically normal estimates (C51) |
GMM framework (C51) | statistical inference without needing to solve the model (C20) |
GMM framework (C51) | addresses the challenge of missing data (C81) |
moment conditions derived from observed data (C51) | identification strategies (Z13) |
transition density of latent variables (C39) | identification strategies (Z13) |
GMM method (C51) | generate draws from the conditional density of latent variables given observed variables (C51) |
quality of moment conditions (C30) | performance of the GMM estimator (C51) |
GMM method (C51) | viable option for frequentist inference in dynamic models with unobserved variables (C32) |