Bootstrap inference for instrumental variable models with many weak instruments. (English) Zbl 1419.62526
Summary: This study’s main contribution is to theoretically analyze the application of bootstrap methods to instrumental variable models when the available instruments may be weak and the number of instruments goes to infinity with the sample size. We demonstrate that a standard residual-based bootstrap procedure cannot consistently estimate the distribution of the limited information maximum likelihood estimator or W. A. Fuller estimator [Econometrica 45, 939–953 (1977; Zbl 0387.62056)] under many/many weak instrument sequence. The primary reason is that the standard procedure fails to capture the instrument strength in the sample adequately. In addition, we consider the restricted efficient (RE) bootstrap of R. Davidson and J. G. MacKinnon [Econom. J. 11, No. 3, 443–477 (2008; Zbl 1154.62018); J. Bus. Econ. Stat. 28, No. 1, 128–144 (2010; Zbl 1198.62035); “Bootstrap confidence sets with weak instruments”, Econ. Rev. 33, No. 5–6, 651–675 (2014; doi:10.1080/07474938.2013.825177)] that generates bootstrap data under the null (restricted) and uses an efficient estimator of the coefficient of the reduced-form equation (efficient). We find that the RE bootstrap is also invalid; however, it effectively mimics more key features in the limiting distributions of interest, and thus, is less distorted in finite samples than the standard bootstrap procedure. Finally, we propose modified bootstrap procedures that provide a valid distributional approximation for the two estimators with many/many weak instruments. A Monte Carlo experiment shows that hypothesis testing based on the asymptotic normal approximation can have severe size distortions in finite samples. Instead, our modified bootstrap procedures greatly reduce these distortions.
MSC:
| 62P20 | Applications of statistics to economics |
| 62J05 | Linear regression; mixed models |
| 62E20 | Asymptotic distribution theory in statistics |
References:
| [1] | Anatolyev, S., Inference in regression models with many regressors, J. Econometrics, 170, 2, 368-382 (2012) · Zbl 1443.62054 |
| [2] | Anatolyev, S.; Gospodinov, N., Specification testing in models with many instruments, Econometric Theory, 27, 2, 427-441 (2011) · Zbl 1215.62016 |
| [3] | Anderson, T. W.; Kunitomo, N.; Matsushita, Y., On the asymptotic optimality of the LIML estimator with possibly many instruments, J. Econometrics, 157, 2, 191-204 (2010) · Zbl 1400.62052 |
| [4] | Anderson, T. W.; Kunitomo, N.; Matsushita, Y., On finite sample properties of alternative estimators of coefficients in a structural equation with many instruments, J. Econometrics, 165, 1, 58-69 (2011) · Zbl 1441.62588 |
| [5] | Andrews, D. W.; Cheng, X., Estimation and inference with weak, semi-strong, and strong identification, Econometrica, 80, 5, 2153-2211 (2012) · Zbl 1274.62160 |
| [6] | Angrist, J.; Imbens, G.; Krueger, A., Jackknife instrumental variables estimation, J. Appl. Econometrics, 14, 1, 57-67 (1999) |
| [7] | Angrist, J. D.; Krueger, A. B., Does compulsory school attendance affect schooling and earnings?, Q. J. Econ., 106, 4, 979-1014 (1991) |
| [8] | Antoine, B.; Renault, E., Efficient GMM with nearly-weak instruments, Econom. J., 12, 1, 135-171 (2009) · Zbl 1182.62032 |
| [9] | Antoine, B.; Renault, E., Efficient minimum distance estimation with multiple rates of convergence, J. Econometrics, 170, 2, 350-367 (2012) · Zbl 1443.62421 |
| [10] | Antoine, B.; Renault, E., Testing identification strength, Discussion Paper dp12-17 (2013), Department of Economics, Simon Fraser University |
| [11] | Bekker, P. A., Alternative approximations to the distributions of instrumental variable estimators, Econometrica, 62, 3, 657-681 (1994) · Zbl 0795.62102 |
| [12] | Bekker, P. A.; Crudu, F., Jackknife instrumental variable estimation with heteroskedasticity, J. Econometrics, 185, 2, 332-342 (2015) · Zbl 1331.62453 |
| [13] | Beran, R., Prepivoting test statistics: A bootstrap view of asymptotic refinements, J. Amer. Statist. Assoc., 83, 403, 687-697 (1988) · Zbl 0662.62024 |
| [14] | Bickel, P. J.; Freedman, D. A., Bootstrapping regression models with many parameters, Festschrift for Erich L. Lehmann, 28-48 (1983) · Zbl 0529.62057 |
| [15] | Brown, B. W.; Newey, W. K., Generalized method of moments, efficient bootstrapping, and improved inference, J. Bus. Econom. Statist., 20, 4, 507-517 (2002) |
| [16] | Chang, Y.; Park, J. Y., A sieve bootstrap for the test of a unit root, J. Time Series Anal., 24, 4, 379-400 (2003) · Zbl 1036.62070 |
| [17] | Chao, J. C.; Hausman, J. A.; Newey, W. K.; Swanson, N. R.; Woutersen, T., Testing overidentifying restrictions with many instruments and heteroskedasticity, J. Econometrics, 178, 15-21 (2014), Part 1 · Zbl 1293.62122 |
| [18] | Chao, J. C.; Swanson, N. R., Consistent estimation with a large number of weak instruments, Econometrica, 73, 5, 1673-1692 (2005) · Zbl 1151.62366 |
| [19] | Chao, J. C.; Swanson, N. R.; Hausman, J. A.; Newey, W. K.; Woutersen, T., Asymptotic distribution of JIVE in a heteroskedastic IV regression with many instruments, Econometric Theory, 28, 1, 42-86 (2012) · Zbl 1442.62734 |
| [20] | Davidson, R.; MacKinnon, J. G., Bootstrap inference in a linear equation estimated by instrumental variables, Econom. J., 11, 3, 443-477 (2008) · Zbl 1154.62018 |
| [21] | Davidson, R.; MacKinnon, J. G., Wild bootstrap tests for IV regression, J. Bus. Econom. Statist., 28, 1, 128-144 (2010) · Zbl 1198.62035 |
| [22] | Davidson, R.; MacKinnon, J. G., Bootstrap confidence sets with weak instruments, Econometric Rev., 33, 5-6, 651-675 (2014) · Zbl 1491.62200 |
| [23] | Donald, S. G.; Newey, W. K., Choosing the number of instruments, Econometrica, 69, 5, 1161-1191 (2001) · Zbl 1021.91047 |
| [24] | Dufour, J.-M., Some impossibility theorems in econometrics with applications to structural and dynamic models, Econometrica, 65, 6, 1365-1387 (1997) · Zbl 0886.62116 |
| [25] | Freedman, D., On bootstrapping two-stage least-squares estimates in stationary linear models, Ann. Statist., 12, 3, 827-842 (1984) · Zbl 0542.62051 |
| [26] | Fuller, W. A., Some properties of a modification of the limited information estimator, Econometrica, 45, 4, 939-953 (1977) · Zbl 0387.62056 |
| [27] | Hall, P.; Horowitz, J. L., Bootstrap critical values for tests based on generalized-method-of-moments estimators, Econometrica, 64, 4, 891-916 (1996) · Zbl 0854.62045 |
| [28] | Hansen, C.; Hausman, J.; Newey, W., Estimation with many instrumental variables, J. Bus. Econom. Statist., 26, 4, 398-422 (2008) |
| [29] | Hasselt, M.v., Many instruments asymptotic approximations under nonnormal error distributions, Econometric Theory, 26, 2, 633-645 (2010) · Zbl 1202.62032 |
| [30] | Hausman, J. A.; Newey, W. K.; Woutersen, T.; Chao, J. C.; Swanson, N. R., Instrumental variable estimation with heteroskedasticity and many instruments, Quant. Econ., 3, 2, 211-255 (2012) · Zbl 1408.62037 |
| [31] | Heyde, C.; Brown, B., On the departure from normality of a certain class of martingales, Ann. Math. Stat., 41, 6, 2161-2165 (1970) · Zbl 0225.60026 |
| [32] | Kleibergen, F., Pivotal statistics for testing structural parameters in instrumental variables regression, Econometrica, 70, 5, 1781-1803 (2002) · Zbl 1141.62361 |
| [33] | Kuersteiner, G.; Okui, R., Constructing optimal instruments by first-stage prediction averaging, Econometrica, 78, 2, 697-718 (2010) · Zbl 1187.62197 |
| [34] | Kunitomo, N., Asymptotic expansions of the distributions of estimators in a linear functional relationship and simultaneous equations, J. Amer. Statist. Assoc., 75, 371, 693-700 (1980) · Zbl 0446.62021 |
| [35] | Mammen, E., Asymptotics with increasing dimension for robust regression with applications to the bootstrap, Ann. Statist., 17, 1, 382-400 (1989) · Zbl 0674.62017 |
| [36] | Mammen, E., Bootstrap and wild bootstrap for high dimensional linear models, Ann. Statist., 21, 1, 255-285 (1993) · Zbl 0771.62032 |
| [37] | Moreira, M. J., A conditional likelihood ratio test for structural models, Econometrica, 71, 4, 1027-1048 (2003) · Zbl 1151.62367 |
| [38] | Moreira, M. J.; Porter, J. R.; Suarez, G. A., Bootstrap validity for the score test when instruments may be weak, J. Econometrics, 149, 1, 52-64 (2009) · Zbl 1429.62065 |
| [39] | Morimune, K., Approximate distributions of k-class estimators when the degree of overidentifiability is large compared with the sample size, Econometrica, 51, 3, 821-841 (1983) · Zbl 0586.62028 |
| [40] | Nagar, A., The bias and moment matrix of the general k-class estimators of the parameters in simultaneous equations, Econometrica, 27, 4, 575-595 (1959) · Zbl 0091.15202 |
| [41] | Newey, W. K.; Windmeijer, F., Generalized method of moments with many weak moment conditions, Econometrica, 77, 3, 687-719 (2009) · Zbl 1176.62055 |
| [42] | Phillips, G. D.A.; Hale, C., The bias of instrumental variable estimators of simultaneous equation systems, Internat. Econom. Rev., 18, 1, 219-228 (1977) · Zbl 0356.62086 |
| [43] | Portnoy, S., Asymptotic behavior of M-estimators of p regression parameters when p \({}^2\)/n is large. I. Consistency, Ann. Statist., 12, 4, 1298-1309 (1984) · Zbl 0584.62050 |
| [44] | Portnoy, S., Asymptotic behavior of M estimators of p regression parameters when p \({}^2\)/n is large; II. Normal approximation, Ann. Statist., 13, 4, 1403-1417 (1985) · Zbl 0601.62026 |
| [45] | Portnoy, S., Asymptotic behavior of likelihood methods for exponential families when the number of parameters tends to infinity, Ann. Statist., 16, 1, 356-366 (1988) · Zbl 0637.62026 |
| [46] | Rothenberg, T. J., Approximating the distributions of econometric estimators and test statistics, (Handbook of Econometrics, vol. 2 (1984)), 881-935 · Zbl 0581.62022 |
| [47] | Staiger, D.; Stock, J. H., Instrumental variables regression with weak instruments, Econometrica, 65, 3, 557-586 (1997) · Zbl 0871.62101 |
| [48] | Stock, J. H.; Yogo, M., Asymptotic distributions of instrumental variables statistics with many instruments, (Identification and Inference for Econometric Models: Essays in Honor of Thomas Rothenberg (2005)), 109-120 · Zbl 1119.62015 |
| [49] | Xiong, S.; Li, G., Some results on the convergence of conditional distributions, Statist. Probab. Lett., 78, 18, 3249-3253 (2008) · Zbl 1489.60005 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
