Optimal Decision Rules for Weak GMM

This paper studies optimal decision rules, including estimators and tests, for weakly identified GMM models. We derive the limit experiment GMM, propose a theoretically?motivated class of priors which give rise to quasi?Bayes rules as limiting case. Together with results in previous literature, this establishes desirable properties approach regardless model identification status, we recommend settings where is concern. further weighted average power?optimal identification?robust frequentist tests confidence sets, prove Bernstein?von Mises?type result posterior under weak identification.