Bayesian Prediction under Moment Conditioning

Abstract

Moment restrictions specify a class of laws, not a predictive model. We obtain one by conditioning an independent sample from a reference law on its empirical moments, and define prediction as the law of a fixed block selected from that conditioned ensemble. On a finite partition this law is an exact mixture over empirical types. Under exact feasibility and lattice regularity, the mixing law has a Gaussian limit on the feasible tangent space, governed by the reduced Hessian, and the selected block approaches independent sampling from the Kullback-Leibler projection. A separate finite-sample bound gives the same product limit for general real-valued restrictions without lattice assumptions. Refinement recovers the projection on the original sample space. Parameterizing the projected family produces a predictive product criterion with a local inverse-covariance expansion, connecting the construction to generalized method of moments.