01960cam a22002537 4500001000600000003000500006005001700011008004100028100001800069245010700087260006600194490005100260500001500311520080400326530006101130538007201191538003601263690005701299690014901356710004201505830008601547856003701633856003601670t0277NBER20160928145755.0160928s2002 mau||||fs|||| 000 0 eng d1 aLee, David S.10aTrimming for Bounds on Treatment Effects with Missing Outcomesh[electronic resource] /cDavid S. Lee. aCambridge, Mass.bNational Bureau of Economic Researchc2002.1 aNBER technical working paper seriesvno. t0277 aJune 2002.3 aEmpirical researchers routinely encounter sample selection bias whereby 1) the regressor of interest is assumed to be exogenous, 2) the dependent variable is missing in a potentially non-random manner, 3) the dependent variable is characterized by an unbounded (or very large) support, and 4) it is unknown which variables directly affect sample selection but not the outcome. This paper proposes a simple and intuitive bounding procedure that can be used in this context. The proposed trimming procedure yields the tightest bounds on average treatment effects consistent with the observed data. The key assumption is a monotonicity restriction on how the assignment to treatment effects selection -- a restriction that is implicitly assumed in standard formulations of the sample selection problem. aHardcopy version available to institutional subscribers. aSystem requirements: Adobe [Acrobat] Reader required for PDF files. aMode of access: World Wide Web. 7aC10 - General2Journal of Economic Literature class. 7aC24 - Truncated and Censored Models • Switching Regression Models • Threshold Regression Models2Journal of Economic Literature class.2 aNational Bureau of Economic Research. 0aTechnical Working Paper Series (National Bureau of Economic Research)vno. t0277.4 uhttp://www.nber.org/papers/t027741uhttp://dx.doi.org/10.3386/t0277