Abstract
Economists rely frequently on instrumental variables estimation to overcome biases that endogenous explanatory variables cause in ordinary least squares estimation. However, traditional instrumental variables estimators, such as two-stage least squares and limited information maximum likelihood estimation, can suffer persistent estimator biases and size-of-test biases in even very large samples if the instruments used are large in number or are only weakly correlated with an endogenous explanatory variable. This paper reviews strategies for grappling with weak instruments and with large numbers of instruments in linear regression models.
Acknowledgments
Daron Acemoglu, Isaiah Andrews, Josh Angrist, Jerry Hausman, Jim Heckman, Simon Johnson, Peter Kennedy, Emily Marshall, Marcelo Moreira, Daniel Riera-Chricton, Carl Schwinn, Paul Shea, Nathan Tefft and Motohiro Yogo provided helpful comments on drafts of this work. Two anonymous referees and the editor, Jack Porter, improved the final version. I am grateful to Vaibhav Bajpai for able research assistance. All errors are mine alone.
References
Acemoglu, Daron, Simon Johnson, and James Robinson. 2001. “The Colonial Origins of Comparative Development: An Empirical Investigation.” American Economic Review 91 (5): 1369–1401.10.3386/w7771Search in Google Scholar
Anderson, T. W. 1974. “An Asymptotic Expansion of the Distribution of the Limited Information Maximum Likelihood Estimate of a Coefficient in a Simultaneous Equation System.” Journal of the American Statistical Association 69: 565–573.10.1080/01621459.1974.10482994Search in Google Scholar
Anderson, T. W., and H. Rubin. 1949. “Estimators of the Parameters of a Single Equation in a Complete Set of Stochastic Equations.” Annals of Mathematical Statistics 21: 570–582.10.1214/aoms/1177729752Search in Google Scholar
Andrews, Isaiah. 2014a. “Conditional Linear Combination Tests for Weakly Identified Models.” Working Paper. MIT (available from author at iandrews@mit.edu).10.3982/ECTA12407Search in Google Scholar
Andrews, Isaiah. 2014b. “Robust Two-Step Confidence Sets, and the Trouble with the First Stage F-Statistic.” Working Paper. MIT (available from author at iandrews@mit.edu).10.2139/ssrn.2373251Search in Google Scholar
Andrews, Donald W. K., and Gustavo Soares. 2007. “Rank Tests for Instrumental Variables Regression with Weak Instruments.” Econometric Theory 23: 1033–1082.10.1017/S0266466607070429Search in Google Scholar
Andrews, Donald W. K., and James H. Stock. 2007a. “Inference with Weak Instruments.” Advances in Econometrics: Proceedings of the Ninth World Congress of the Econometric Society 3.10.3386/t0313Search in Google Scholar
Andrews, Donald W. K., and James H. Stock. 2007b. “Testing with Many Weak Instruments.” Journal of Econometrics 138 (1): 24–46.10.1016/j.jeconom.2006.05.012Search in Google Scholar
Andrews, Donald W. K., Marcelo Moreira, and James H. Stock. 2004. “Optimal Two-sided Invariant Similar Tests for Instrumental Variables Regression.” Cowles Foundation Discussion Paper No. 1476.10.1111/j.1468-0262.2006.00680.xSearch in Google Scholar
Andrews, Donald W. K., Marcelo Moreira, and James H. Stock. 2006. “Optimal Two-sided Invariant Similar Tests for Instrumental Variables Regression.” Econometrica 74 (3): 715–752.10.1111/j.1468-0262.2006.00680.xSearch in Google Scholar
Angrist, Joshua D., and Alan Krueger. 1991. “Does Compulsory School Attendance Affect Schooling and Earnings?” Quarterly Journal of Economics 106 (4): 979–1014.10.3386/w3572Search in Google Scholar
Angrist, Joshua D., Guido W. Imbens, and Daniel Rubin. 1996. “Identification of Causal Effects Using Instrumental Variables (with Discussion).” Journal of the American Statistical Association 91: 444–472.10.1080/01621459.1996.10476902Search in Google Scholar
Baum, Christopher F., Mark E. Schaffer, and Steven Stillman. 2003. “Instrumental Variables and GMM: Estimation and Testing.” Stata Journal (3): 1–31.10.1177/1536867X0300300101Search in Google Scholar
Baum, Christopher F., Mark E. Schaffer, and Steven Stillman. 2007a. “Enhanced Routines for Instrumental Variables/GMM Estimation and Testing.” Stata Journal 7 (4): 465–506.10.1177/1536867X0800700402Search in Google Scholar
Baum, Christopher F., Mark E. Schaffer, and Stephen Stillman. 2007b. “ivreg2: Stata Module for Extended Instrumental Variables/2SLS, GMM and AC/HAC, LIML, and k-class Regression.” Boston College Department of Economics, Statistical Software Components S425401. http://ideas.repec.org/c/boc/bocode/s425401.html.Search in Google Scholar
Bekker, Paul A. 1994. “Alternative Approximations to the Distribution of Instrumental Variables Estimators.” Econometrica 63: 657–681.10.2307/2951662Search in Google Scholar
Bekker, Paul A., and Jan van der Ploeg. 2005. “Instrumental Variable Estimation Based on Grouped Data.” Statistica Neerlandica 59 (3): 239–267.10.1111/j.1467-9574.2005.00296.xSearch in Google Scholar
Bekker, Paul A., and Federico Crudu. 2014. “Jackknife Instrumental Variable Estimation with Heteroskedasticity.” Working Paper. http://www.rug.nl/staff/p.a.bekker/heteroskedsticityestimatorbc-february2014.pdf.10.1016/j.jeconom.2014.08.012Search in Google Scholar
Breusch, Trevor, Hailong Qian, Peter Schmidt, and Donald Wyhowski. 1999. “Redundancy of Moment Conditions.” Journal of Econometrics 91: 89–111.10.1016/S0304-4076(98)00050-5Search in Google Scholar
Carneiro, Pedro, James J. Heckman, and Edward Vytlacil. 2011. “Estimating Marginal and Average Returns to Education.” American Economic Review 101 (6): 2754–2781.10.1257/aer.101.6.2754Search in Google Scholar
Chernozhukov, Victor, and Christian Hansen. 2008. “The Reduced Form: A Simple Approach to Inference with Weak Instruments.” Economics Letters 100 (1): 68–71.10.1016/j.econlet.2007.11.012Search in Google Scholar
Chao, J. C., and N. R. Swanson. 2004. “Estimation and Testing Using Jackknife IV in Heteroskedastic Regressions with Many Weak Instruments.” Working Paper. Rutgers University.10.2139/ssrn.592803Search in Google Scholar
Chao, John C., Jerry Hausman, Whitney Newey, Norman Swanson, and Tieman Woutersen. 2010. “Testing Overidentifying Restrictions with Many Instruments and Heteroskedasticity.” Presented at the Test 2010 Conference, Xiamen, China.10.2139/ssrn.1856081Search in Google Scholar
Chao, John C., Norman R. Swanson, Jerry A. Hausman, Whitney K. Newey, and Tiemen Woutersen. 2012. “Asymptotic Distribution of JIVE in a Heteroskedastic IV Regression with Many Instruments.” Econometric Theory 28 (1): 42–86.10.1017/S0266466611000120Search in Google Scholar
Cragg, John G., and Stephen G. Donald. 1993. “Testing Identifiability and Specification in Instrumental Variable Models.” Econometric Theory 9 (2): 222–240.10.1017/S0266466600007519Search in Google Scholar
Cruz, Luiz M., and M. Moreira. 2005. “On the Validity of Econometric Techniques with Weak Instruments: Inference on Returns to Education Using Compulsory School Attendance Laws.” Journal of Human Resources 40 (2): 393–410.10.3368/jhr.XL.2.393Search in Google Scholar
Davidson, Russell, and James G. MacKinnon. 1993. Estimation and Inference in Econometrics. Oxford: Oxford University Press.Search in Google Scholar
Dufour, Jean-Marie. 1997. “Some Impossibility Theorems in Econometrics With Applications to Structural and Dynamic Models.” Econometrica 45 (6): 1365–1387.10.2307/2171740Search in Google Scholar
Epstein, Larry G., and Stanley E. Zin. 1989. “Substitution, Risk Aversion, and the Temporal Behavior of Consumption and Asset Returns: A Theoretical Framework.” Econometrica 57 (4): 937–969.10.1142/9789814417358_0012Search in Google Scholar
Finlay, Keith, and Leandro M. Magnusson. 2009. “Implementing Weak-instrument Robust tests for a General Class of Instrumental-variables Models.” The Stata Journal 9 (3): 1–24.10.1177/1536867X0900900304Search in Google Scholar
Fuller, Wayne A. 1977. “Some Properties of a Modification of the Limited Information Maximum Likelihood Estimator.” Econometrica 45: 939–954.10.2307/1912683Search in Google Scholar
Glaeser, E. L., R. La Porta, F. Lopez-de-Silanes, and A. Shleifer. 2004. “Do Institutions Cause Growth?” NBER Working Paper #10568.10.3386/w10568Search in Google Scholar
Hall, Robert E. 1988. “Intertemporal Substitution in Consumption.” Journal of Political Economy 96 (2): 339–357.10.3386/w0720Search in Google Scholar
Hall, A. R., G. D. Rudebusch, and D. W. Wilcox. 1996. “Judging Instrument Relevance in Instrumental Variables Estimation.” International Economic Review 37: 283–298.10.2307/2527324Search in Google Scholar
Han, Chirok, and Peter C. B. Phillips. 2006. “GMM with Many Moment Conditions.” Econometrica 74 (1): 147–192.10.1111/j.1468-0262.2006.00652.xSearch in Google Scholar
Hahn, Jinyong, and Atsushi Inoue. 2002. “A Monte Carlo Comparison of Various Asymptotic Approximations to the Distribution of Instrumental Variables Estimators.” Econometric Reviews 21: 309–336.10.1081/ETC-120015786Search in Google Scholar
Hahn, Jinyong, and Jerry Hausman. 2005. “Instrumental Variable Estimation with Valid and Invalid Instruments.” Annales d’Economie et Statistique 79/80: 25–57.10.2307/20777569Search in Google Scholar
Hahn, Jinyong, Jerry Hausman, and Guido Kuersteiner. 2004. “Estimation with Weak Instruments: Accuracy of Higher Order Bias and MSE Approximations.” Econometrics Journal 7: 272–306.10.1111/j.1368-423X.2004.00131.xSearch in Google Scholar
Hahn, Jinyong, John C. Ham, and Hyungsik Roger Moon. 2011. “The Hausman Test and Weak Instruments.” Journal of Econometrics 160 (2): 289–299.10.1016/j.jeconom.2010.09.009Search in Google Scholar
Hansen, Lars P., and Kenneth J. Singleton. 1983. “Stochastic Consumption, Risk Aversion, and the Temporal Behavior of Asset Returns.” Journal of Political Economy 91 (2): 249–265.10.1086/261141Search in Google Scholar
Hansen, C., J. Hausman, and W. Newey. 2008. “Estimation with Many Instrumental Variables.” Journal of Business and Economics Statistics 26 (4): 398–422.10.1920/wp.cem.2006.1906Search in Google Scholar
Hausman, Jerry. 1983. “Specification and Estimation of Simultaneous Equations.” Handbook of Econometrics, Vol. 1, Chapter 7, North Holland, Amsterdam: Elsevier, 391516.10.1016/S1573-4412(83)01011-9Search in Google Scholar
Hausman, Jerry A., Whitney K. Newey, Tiemen Woutersen, John C. Chao, and Norman R. Swanson. 2012. “Instrumental Variable Estimation with Heteroskedasticity and Many Instruments.” Quantitative Economics 3 (2): 211–255.10.1920/wp.cem.2007.2207Search in Google Scholar
Heckman, James J. 1990. “Varieties of Selection Bias.” American Economic Review, Papers and Proceedings 80: 313–338.Search in Google Scholar
Heckman, James J., and Edward Vytlacil. 2005. “Structural Equations, Treatment Effects and Econometric Policy Evaluation.” Econometrica 73: 669–738.10.1111/j.1468-0262.2005.00594.xSearch in Google Scholar
Heckman, James J., and Sergio Urzua. 2009. “Comparing IV with Structural Models: What Simple IV Can and Cannot Identify.” National Bureau of Economic Research, Working Paper, 14706.Search in Google Scholar
Imbens, Guido W., and Joshua D. Angrist,. 1994. “Identification and Estimation of Local Average Treatment Effects.” Econometrica 62 (2): 467–475.10.2307/2951620Search in Google Scholar
Kleibergen, Frank. 2002. “Pivotal Statistics for Testing Structural Parameters in Instrumental Variables Regression.” Econometrica 70: 1781–1803.10.1111/1468-0262.00353Search in Google Scholar
Kleibergen, Frank. 2004. “Testing Subsets of Structural Parameters in the Instrumental Variables Regression Model.” Review of Economics and Statistics 86: 418–423.10.1162/003465304774201833Search in Google Scholar
Kleibergen, Frank. 2005. “Testing Parameters in GMM without Assuming That They Are Identified.” Econometrica 73 (4): 1103–1123.10.1111/j.1468-0262.2005.00610.xSearch in Google Scholar
Kleibergen, Frank. 2007. “Generalizing Weak Instrument Robust IV Statistics Towards Multiple Parameters, Unrestricted Covariance Matrices and Identification Statistics.” Journal of Econometrics 139 (1): 181–216.10.1016/j.jeconom.2006.06.010Search in Google Scholar
Kleibergen, Frank. 2008. “Size Correct Subset Statistics in the Linear IV Regression Model.” Working paper, Brown University.Search in Google Scholar
Kleibergen, Frank, and Richard Paap. 2006. “Generalized Reduced Rank Tests Using the Singular Value Decomposition.” Journal of Econometrics 133: 97–126.10.1016/j.jeconom.2005.02.011Search in Google Scholar
Kleibergen, Frank, and Marc Schaffer. 2007. “Ranktest: Stata Module to Test the Rank of a Matrix Using the Kleibergen–Paap rk Statistic.” Boston College Department of Economics, Statistical Software Components S456865. http://ideas.repec.org/c/boc/bocode/s456865.html.Search in Google Scholar
Kolesar, Michal. 2013. “Estimation in an Instrumental Variables Model with Treatment Effect heterogeneity.” Working paper. Accessed August 24, 2014. https://www.princeton.edu/~mkolesar/papers/late-estimation.pdf.Search in Google Scholar
Kunitomo, Naoto. 1980. “Asymptotic Expansions of the Distributions of Estimators in a Linear Functional Relationship and Simultaneous Equations.” Journal of the American Statistical Society 75: 693–700.10.1080/01621459.1980.10477535Search in Google Scholar
Longfellow, Henry W. 1922. Random Memories. Boston: Houghton Mifflin.Search in Google Scholar
Mikusheva, A. 2005. “An Algorithm for Constructing Confidence Intervals Robust to Weak Instruments.” mimeo, Cambridge, MA, October.10.2139/ssrn.1021366Search in Google Scholar
Mikusheva, Anna. 2010. “Robust Confidence Sets in the Presence of Weak Instruments.” Journal of Econometrics 157: 236–247.10.1016/j.jeconom.2009.12.003Search in Google Scholar
Mikusheva, Anna, and B. Poi. 2006. “Tests and Confidence Sets with Correct Size in the Simultaneous Equations Model with Potentially Weak Instruments.” Stata Journal 6 (3): 335–347.10.1177/1536867X0600600303Search in Google Scholar
Moreira, Marcelo J. 2003. “A Conditional Likelihood Test for Structural Models.” Econometrica 71 (4): 1027–1048.10.1111/1468-0262.00438Search in Google Scholar
Moreira, Humberto, and Marcelo J. Moreira. 2013. “Contributions to the Theory of Optimal Tests.” Working Paper, Undação Getúlio Vargas.Search in Google Scholar
Morimune, Kimio. 1983. “Approximate Distributions of k-Class Estimators when the Degree of Overidentifiability is Large Compared with the Sample Size.” Econometrica 51: 821–842.10.2307/1912160Search in Google Scholar
Murray, M. P. 2005. “The Bad, the Weak, and the Ugly: Avoiding the Pitfalls of Instrumental Variables Estimation” Social Science Research Network working paper #843185.Search in Google Scholar
Nelson, C., and R. Startz. 1990a. “Some Further Results on the Exact Small Sample Properties of the Instrumental Variables Estimator.” Econometrica 58 (4): 967–976.10.3386/t0068Search in Google Scholar
Nelson, C., and R. Startz. 1990b. “The Distribution of the Instrumental Variables Estimator and Its f-Ratio When the instrument Is a Poor One.” Journal of Business 63 (1): S125–S140.10.1086/296497Search in Google Scholar
Newey, Whitney K., and Frank Windmeijer. 2009. “Generalized Method of Moments with Many Weak Moment Conditions.” Econometrica 77 (3): 687–719.10.3982/ECTA6224Search in Google Scholar
Olea, J. L. M., and C. Pflueger. 2013. “A Robust Test for Weak Instruments.” Journal of Business & Economic Statistics 31 (3): 358–369.10.1080/00401706.2013.806694Search in Google Scholar
Pagan, Adrian Rodney, and Anthony David Hall. 1983. “Diagnostic Tests as Residual Analysis.” Econometric Reviews 2 (2): 159–218.10.1080/07311768308800039Search in Google Scholar
Pesaran, Hashem M., and Larry W. Taylor. 1999. “Diagnostics for IV Regressions.” Oxford Bulletin of Economics and Statistics 61 (2): 255–281.10.1111/1468-0084.00128Search in Google Scholar
Phillips, Peter C. B. 1983. “Exact Small Sample Theory in the Simultaneous Equations Model.” Handbook of Econometrics 1: 449–516.10.1016/S1573-4412(83)01012-0Search in Google Scholar
Rothenberg, Thomas J. 1983. “Asymptotic Properties of Some Estimators in Structural Models.” In Studies in Econometrics, Time Series, and Multivariate Statistics, in honor of T. W. Anderson, edited by S. Karlin, T. Amemiya, and L. A. Goodman. Academic Press.10.1016/B978-0-12-398750-1.50013-9Search in Google Scholar
Rothenberg, Thomas J. 1984. “Approximating the Distributions of Econometric Estimators and Test Statistics.” Chapter 15 in Handbook of Econometrics vol. 2, edited by Z. Griliches and M. D. Intriligator, North Holland, Amsterdam: Elsevier, 881–935.10.1016/S1573-4412(84)02007-9Search in Google Scholar
Rubin, D. 1974. “Estimating Causal Effects of Treatments in Randomized and Non-randomized Studies.” Journal of Educational Psychology 66: 688–701.10.1037/h0037350Search in Google Scholar
Staiger, Douglas, and James H. Stock. 1997. “Instrumental Variables Regressions with Weak Instruments.” Econometrica 65 (3): 557–586.10.3386/t0151Search in Google Scholar
Stock, James H., and Motohiro Yogo. 2005. “Testing for Weak Instruments in IV Regression.” In Identification and Inference for Econometric Models: A Festschrift in Honor of Thomas Rothenberg, 1, Cambridge University Press.10.1017/CBO9780511614491Search in Google Scholar
Stock, James H., Jonathan H. Wright, and Motohiro Yogo. 2002. “A Survey of Weak Instruments and Weak Identification in Generalized Method of Moments.” Journal of Business and Economic Statistics 20 (4): 518–529.10.1198/073500102288618658Search in Google Scholar
Tsurumi, Hiroki. 1990. “Comparing Bayesian and Non-Bayesian Limited Information Estimators.” In Bayesian and Likelihood Methods in Statistics and Econometrics: Essays in Honor of George Barnard. North-Holland, Amsterdam, 179–207.Search in Google Scholar
White, Halbert. 1980. “A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity.” Econometrica 48 (4): 817–838.10.2307/1912934Search in Google Scholar
Yogo, Motohiro. 2004. “Estimating the Elasticity of Intertemporal Substitution When Instruments are Weak.” Review of Economics and Statistics 86 (3): 797–810.10.1162/0034653041811770Search in Google Scholar
©2017 Walter de Gruyter GmbH, Berlin/Boston