Instrumental variables are commonly used to estimate treatment effects in cases of imperfect compliance. However, if participation in the program is misreported, standard techniques can yield severely biased results. We present a new command, ivreg2m, that implements the mismeasured robust local average treatment-effect estimator developed by Calvi, Lewbel, and Tommasi (2022, Journal of Business and Economic Statistics 40: 1701–1717) and Tommasi and Zhang (2024b, Journal of Applied Econometrics,https://doi.org/10.1002/jae.3079), to estimate the heterogeneous treatment effect of a program in the presence of treatment noncompliance and misreporting. The ivreg2m command can be used as the preferred strategy in cases of exogenous (nondifferential) misclassification.
AtheyS.ImbensG. W.. 2017. The econometrics of randomized experiments. In Vol. 1 of Handbook of Economic Field Experiments, ed. A. V. Banerjee and E. Duflo, 73-140. Amsterdam: North-Holland. 10.1016/bs.hefe.2016.10.003.
2.
Battistin, E., M. De Nadai, and B. Sianesi. 2014. Misreported schooling, multiple measures and returns to educational qualifications. Journal of Econometrics181: 136–150. 10.1016/j.jeconom.2014.03.002.
3.
BaumC. F.SchafferM. E.StillmanS.. 2003. Instrumental variables and GMM: Estimation and testing. Stata Journal3: 1–31. 10.1177/1536867X0300300101.
4.
__________. 2007. Enhanced routines for instrumental variables/generalized method of moments estimation and testing. Stata Journal7: 465–506. 10.1177/1536867X0800700402.
5.
CalviR.LewbelA.TommasiD.. 2022. LATE with missing or mismeasured treatment. Journal of Business and Economic Statistics40: 1701–1717. 10.1080/07350015.2021.1970573.
6.
DiTragliaF. J.Garci-JimenoC.. 2019. Identifying the effect of a mis-classified, binary, endogenous regressor. Journal of Econometrics209: 376–390. 10.1016/j.jeconom.2019.01.007.
7.
ImbensG. W.AngristJ. D.. 1994. Identification and estimation of local average treatment effects. Econometrica62: 467–475. 10.2307/2951620.
8.
KasaharaH.ShimotsuK.. 2022. Identification of regression models with a mis- classified and endogenous binary regressor. Econometric Theory38: 1117–1139. 10.1017/S0266466621000451.
9.
Kleibergen, F., and M. E. Schaffer. 2007. ranktest: Stata module to test the rank of a matrix using the Kleibergen-Paap rk statistic. Statistical Software Components S456865, Department of Economics, Boston College. https://ideas.repec.org/c/boc/bocode/s456865.html.
10.
KreiderB. 2010. Regression coefficient identification decay in the presence of infrequent classification errors. Review of Economics and Statistics92: 1017–1023. 10.1162/REST_a_00044.
11.
KreiderB.PepperJ. V.GundersenC.JolliffeD.. 2012. Identifying the effects of SNAP (food stamps) on child health outcomes when participation is endogenous and misreported. Journal of the American Statistical Association107: 958–975. 10.1080/01621459.2012.682828.
12.
LinA.TommasiD.ZhangL.. 2024. Bounding program benefits when participation is misreported: Estimation and inference with Stata. Stata Journal24: 185–212. 10.1177/1536867X241257347.
13.
McCarthyI.MillimetD. L.RoyM.. 2015. Bounding treatment effects: A command for the partial identification of the average treatment effect with endogenous and misreported treatment assignment. Stata Journal15: 411–436. 10.1177/1536867X1501500205.
14.
MillimetD. L. 2011. The elephant in the corner: A cautionary tale about measurement error in treatment effects models. In Advances in Econometrics. Vol. 27, Missing- Data Methods: Cross-sectional Methods and Applications, ed. DrukkerD. M., 1–39. Bingley, UK: Emerald. 10.1108/S0731-9053(2011)000027A004.
15.
MogstadM.TorgovitskyA.WaltersC. R.. 2021. The causal interpretation of two-stage least squares with multiple instrumental variables. American Economic Review111: 3663–3698. 10.1257/aer.20190221.
16.
Newey, W. K., and K. D. West.1987. A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica 55: 703-708. 10.2307/1913610.
17.
Nguimkeu, P., A. Denteh, and R. Tchernis.2019. On the estimation of treatment effects with endogenous misreporting. Journal of Econometrics 208: 487-506. 10.1016/j.jeconom.2018.10.005.
18.
SchafferM. E.2005. xtivreg2: Stata module to perform extended IV/2SLS, GMM and AC/HAC, LIML, and k-class regression for panel-data models. Statistical Software Components S456501, Department of Economics, Boston College. https://ideas.repec.org/c/boc/bocode/s456501.html.
19.
TommasiD.2019. Control of resources, bargaining power and the demand of food: Evidence from PROGRESA. Journal of Economic Behavior and Organization 161: 265-286. 10.1016/j.jebo.2019.04.008.
20.
Tommasi, D., and L. Zhang.2022. Identifying program benefits when participation is misreported. IZA Discussion Paper 15427, Institute of Labor Economics (IZA). https://docs.iza.org/dp15427.pdf.
21.
_________. 2024a. Bounding program benefits when participation is misreported. Journal of Econometrics 238: art. 105556. 10.1016/j.jeconom.2023.105556.
22.
_________. 2024b. Identifying program benefits when participation is misreported. Journal of Applied Econometrics 39: 1123-1148. 10.1002/jae.3079.
YanagiT.2019. Inference on local average treatment effects for misclassified treatment. Econometric Reviews 38: 938-960. 10.1080/07474938.2018.1485833.
