Authors	Becker, S.O. and Caliendo, M.
Year	2007
Reference	Stata Journal, 7(1), 71-83.
Keywords	Matching, Treatment Effects, Sensitivity Analysis, Unobserved Heterogeneity.
Download	IZA Discussion Paper No. 2542: PDF Download zipped ado- and help-file here: mhbounds.zip Download zip-file including example data here: mhbounds_all.zip
Instructions	Download the zip-file and unpack mhbounds.ado and mhbounds.hlp in your local Stata ado-directory. We are continuously improving our programs: please check out for updates. The current version is dated 16 August 2006.
Abstract	Matching has become a popular approach to estimate average treatment effects. It is based on the conditional independence or unconfoundedness assumption. Checking the sensitivity of the estimated results with respect to deviations from this identifying assumption becomes an increasingly important topic in the applied evaluation literature. If there are unobserved variables which affect assignment into treatment and the outcome variable simultaneously, a hidden bias might arise to which matching estimators are not robust. We address this problem with the bounding approach proposed by Rosenbaum (2002), where mhbounds allows the researcher to determine how strongly an unmeasured variable must influence the selection process in order to undermine the implications of the matching analysis.