Abstract
The paper studies the asymptotic size property of various specification tests in linear structural models where instrumental variables may locally violate the exclusion restrictions. Our results provide some new insights and extensions of earlier studies. In particular, we derive an explicit formula of the asymptotic size of the tests which shows clearly the factors that influence their size under instrument endogeneity. We show that all tests have correct asymptotic size when the usual orthogonality condition holds, but their asymptotic size can be arbitrary large even if only one instrument is slightly correlated with the error term. We present a Monte Carlo experiment that confirms our theoretical findings.
Acknowledgements
We are grateful to the Editor Prof. N. Balakrishnan and the anonymous referees for their constructive comments and suggestions. We would like to thank Jean-Marie Dufour and Mardi Dungey for very helpful comments. The first draft of this paper was circulated as ‘Specification Testing with Weak and Invalid Instruments’.
Notes
3 See Durbin (Citation1954), Wu (Citation1973, Citation1974), Hausman (Citation1978), Nakamura and Nakamura (Citation1981, Citation1985), Engle (Citation1982), Holly (Citation1982, Citation1983b,a), Holly and Monfort (Citation1983), Reynolds (Citation1982), Smith (Citation1983, Citation1984, Citation1985), Staiger and Stock (Citation1997), Kiviet and Niemczyk (Citation2006, Citation2007), Hahn, Ham, and Moon (Citation2010), Kiviet (Citation2013), Doko Tchatoka (Citation2015), and Doko Tchatoka and Dufour (Citation2016b,a).
5 The first-stage F-statistic corresponds to the concentration parameter ![](//:0)
that controls identification strength of β in the notation of Staiger and Stock (Citation1997).
Durbin, J. 1954. Errors in variables. Review of the International Statistical Institute 22:23–32. Wu, D.-M. 1973. Alternative tests of independence between stochastic regressors and disturbances. Econometrica 41:733–50. Wu, D.-M. 1974. Alternative tests of independence between stochastic regressors and disturbances: Finite sample results. Econometrica 42:529–46. Durbin, J. 1954. Errors in variables. Review of the International Statistical Institute 22:23–32. Wu, D.-M. 1973. Alternative tests of independence between stochastic regressors and disturbances. Econometrica 41:733–50. Wu, D.-M. 1974. Alternative tests of independence between stochastic regressors and disturbances: Finite sample results. Econometrica 42:529–46. Hausman, J. 1978. Specification tests in econometrics. Econometrica 46:1251–72. Nakamura, A., and M. Nakamura. 1981. On the relationships among several specification error tests presented by Durbin, Wu and Hausman. Econometrica 49:1583–88. Nakamura, A., and M. Nakamura. 1985. On the performance of tests by Wu and by Hausman for detecting the ordinary least squares bias problem. Journal of Econometrics 29:213–27. Engle, R. F. 1982. A general approach to Lagrange multiplier diagnostics. Journal of Econometrics 20:83–104. Holly, A. 1982. A remark on Hausman’s test. Econometrica 50:749–59. Holly, A. 1983b. Une présentation unifiée des tests d’exogénéity dans les modèles à equations simultanées. Annales de l’INSEE 50:3–24. Holly, A., and A. Monfort. 1983. Some useful equivalence properties of Hausman’s test. Economics Letters 20:39–43. Reynolds, R. A. 1982. Posterior odds for the hypothesis of independence between stochastic regressors and disturbances. International Economic Review 23 (2):479–90. Smith, R. J. 1983. On the classical nature of the Wu-Hausman statistics for independence of stochastic regressors and disturbance. Economics Letters 11:357–64. Smith, R. J. 1984. A note on likelihood ratio tests for the independence between a subset of stochastic regressors and disturbances. International Economic Review 25:263–69. Smith, R. J. 1985. Wald tests for the independence of stochastic variables and disturbance of a single linear stochastic simultaneous equation. Economics Letters 17:87–90. Staiger, D., and J. H. Stock. 1997. Instrumental variables regression with weak instruments. Econometrica 65 (3):557–86. Kiviet, J. F., and J. Niemczyk. 2006. On the limiting and empirical distribution of IV estimators when some of the instruments are invalid. Technical report, Department of Quantitative Economics, University of Amsterdam Amsterdam, The Netherlands. Kiviet, J. F., and J. Niemczyk. 2007. The asymptotic and finite-sample distributions of OLS and simple IV in simultaneous equations. Computational Statistics and Data Analysis 51:3296–18. Hahn, J., J. Ham, and H. R. Moon. 2010. The Hausman test and weak instruments. Journal of Econometrics 160:289–99. Kiviet, J. F. 2013. Identification and inference in a simultaneous equation under alternative information sets and sampling schemes. The Econometrics Journal 16:S24–S59. Doko Tchatoka, F. 2015. On bootstrap validity for specification tests with weak instruments. The Econometrics Journal 18 (1):137–46. Doko Tchatoka, F., and J.-M. Dufour. 2016b. Exogeneity tests, weak identification, incomplete models and non-gaussian distributions: Invariance and finite-sample distributional theory. Technical report, Department of Economics, McGill University Montréal, Canada. Staiger, D., and J. H. Stock. 1997. Instrumental variables regression with weak instruments. Econometrica 65 (3):557–86.