Abstract:
|
A linear rational-expectations model (LREM) is specified in terms of a linear (in variables and disturbances) structural equation that determines how endogenous variables are generated and a separate linear process that determines how exogenous variables are generated. The structural equation is solved for a linear rational expectations solution (RES) equation, which, for an assumed linear exogenous vector autoregressive (VAR) process, reduces to a linear reduced-form (RF) equation. The paper contributes by deriving linear identification 1 of structural coefficients from RES coefficients and linear identification 2 of RES coefficients from RF coefficients. An identification is a unique determination of coefficients (or underlying deep parameters) down from assumed data moments. Identifications 1-2 are linear because their determining equations are linear. An identification becomes a consistent estimation if it's a unique determination down from consistently estimated data moments. Identifications 1-2 require only exogenous variables and generic rank conditions on coefficient matrices and don't require any exact restrictions on coefficients. Therefore, as estimations, combined ident
|