CONSTRAINT QUALIFICATIONS IN PARTIAL IDENTIFICATION

The literature on stochastic programming typically restricts attention to problems that fulfill constraint qualifications. estimation and inference under partial identification frequently the geometry of identified sets with diverse high-level assumptions. These superficially appear be different approaches closely related problems. We extensively analyze their relation. Among other things, we show for through pure moment inequalities, numerous assumptions from essentially coincide Mangasarian–Fromowitz qualification. This clarifies relation between well-known contributions, including within econometrics, elucidates stringency, as well ease verification, some in seminal papers.