12
mhbounds
sensitive to possible deviations from the identifying unconfoundedness assumption and
hence, some caution when interpreting the results is advisable.
6 Saved Results
mhbounds produces the matrix outmat containing the Mantel-Haenszel test statistics
for all values of Γ specified by the user. When the option stratamat is specified in
conjunction with stratum(varname), mhbounds keeps in memory not only the matrix
outmat containing the overall/combined test statistics, but also the matrices outmatj
containing the strata-specific test statistics, j = 1, ...,#strata.
7 Acknowledgments
We thank Tommaso Nannicini for very useful suggestions.
8 References
Abadie, A. and Drukker, D. and Leber Herr, J. and Imbens, G.W. (2004), “Imple-
menting Matching Estimators for Average Treatment Effects in STATA”, Stata
Journal 4(3), 290-311.
Aakvik, A. (2001), “Bounding a Matching Estimator: The Case of a Norwegian Train-
ing Program”, Oxford Bulletin of Economics and Statistics 63(1), 115-143.
Becker, S.O. and Ichino, A. (2002), “Estimation of average treatment effects based on
propensity scores”, Stata Journal 2(4), 358-377.
Caliendo, M., Hujer, R. and Thomsen, S. (2005), “The Employment Effects of Job
Creation Schemes in Germany”, IZA-Discussion Paper No. 1512, Bonn.
Caliendo, M. and Kopeinig, S. (2006), “Some Practical Guidance for the Implementa-
tion of Propensity Score Matching”, IZA Discussion Paper No. 1588, forthcoming
in Journal of Economic Surveys.
Dehejia, R.H. and Wahba, S. (1999), “Causal Effects in Nonexperimental Studies:
Reevaluation of the Evaluation of Training Programs”, Journal of the American
Statistical Association 94, 1053-1062.
DiPrete, T. and Gangl, M. (2005), “Assessing Bias in the Estimation of Causal Ef-
fects: Rosenbaum Bounds on Matching Estimators and Instrumental Variables
Estimation with Imperfect Instruments”, Sociological Methodology 35.
Heckman, J.J., Ichimura, H., Smith, J. and Todd, P. (1998), “Characterizing Selection
Bias Using Experimental Data,” Econometrica, 66(5), 1017-1098.