The two-stage least-squares (2SLS) instrumental variables estimator is commonly used to address endogeneity. However, the estimator suffers from bias that is exacerbated when the instruments are only weakly correlated with the endogenous variables and when many instruments are used. In this article, I discuss jackknife instrumental variables estimation as an alternative to 2sls. Monte Carlo simulations comparing the jackknife instrument variables estimators to 2sls and limited information maximum likelihood (liml) show that two of the four variants perform remarkably well even when 2sls does not. In a weak-instrument experiment, the two best performing jackknife estimators also outperform liml.
AngristJ. D., ImbensG. W., and KruegerA. B.1999. Jackknife instrumental variables estimation. Journal of Applied Econometrics14: 57–67.
2.
AngristJ. D., and KruegerA. B.1991. Does compulsory school attendance affect schooling and earnings?Quarterly Journal of Economics106: 979–1014.
3.
BaumC. F., SchafferM. E., and StillmanS.2003. Instrumental variables and GMM: Estimation and testing. Stata Journal3: 1–31.
4.
BaumC. F.2004. Software updates: Instrumental variables and GMM: Estimation and testing. Stata Journal4: 224.
5.
BaumC. F.2005. Software updates: Instrumental variables and GMM: Estimation and testing. Stata Journal5: 607.
6.
BlomquistS., and DahlbergM.1999. Small sample properties of LIML and jackknife IV estimators: Experiments with weak instruments. Journal of Applied Econometrics14: 69–88.
7.
BoundJ., JaegerD., and BakerR.1995. Problems with instrumental variable estimation when the correlation between the instruments and the endogenous explanatory variables is weak. Journal of the American Statistical Association90: 443–450.
MikushevaA., and PoiB. P.2006. Tests and confidence sets with correct size when instruments are potentially weak. Stata Journal6. 51–63.
10.
MoreiraM. J., and PoiB. P.2003. Implementing tests with correct size in the simultaneous equations model. Stata Journal3: 57–70.
11.
NagarA. L.1959. The bias and moment matrix of the general k-class estimators of the parameters in simultaneous equations. Econometrica27: 575–595.
12.
NelsonC. R., and StartzR.1990. The distribution of the instrumental variables estimator and its t-ratio when the instrument is a poor one. Journal of Business63: 5125–5140.
13.
PhillipsG. D. A., and HaleC.1977. The bias of instrumental variable estimators of simultaneous equation systems. International Economic Review18: 219–228.
14.
StockJ. H., WrightJ. H., and YogoM.2002. A survey of weak instruments and weak identification in generalized method of moments. Journal of Business and Economic Statistics20: 518–529.
