Abstracts
Résumé
Cet article illustre l’applicabilité des méthodes de rééchantillonnage dans le cadre des tests multiples (simultanés), pour divers problèmes économétriques. Les hypothèses simultanées sont une conséquence habituelle de la théorie économique, de sorte que le contrôle de la probabilité de rejet de combinaisons de tests est un problème que l’on rencontre fréquemment dans divers contextes économétriques et statistiques. À ce sujet, on sait que le fait d’ignorer le caractère conjoint des hypothèses multiples peut faire en sorte que le niveau de la procédure globale dépasse considérablement le niveau désiré. Alors que la plupart des méthodes d’inférence multiple sont conservatrices en présence de statistiques non indépendantes, les tests que nous proposons visent à contrôler exactement le niveau de signification. Pour ce faire, nous considérons des critères de test combinés proposés initialement pour des statistiques indépendantes. En appliquant la méthode des tests de Monte-Carlo, nous montrons comment ces méthodes de combinaison de tests peuvent s’appliquer à de tels cas, sans recours à des approximations asymptotiques. Après avoir passé en revue les résultats antérieurs sur ce sujet, nous montrons comment une telle méthodologie peut être utilisée pour construire des tests de normalité basés sur plusieurs moments pour les erreurs de modèles de régression linéaires. Pour ce problème, nous proposons une généralisation valide à distance finie du test asymptotique proposé par Kiefer et Salmon (1983) ainsi que des tests combinés suivant les méthodes de Tippett et de Pearson-Fisher. Nous observons empiriquement que les procédures de test corrigées par la méthode des tests de Monte-Carlo ne souffrent pas du problème de biais (ou sous-rejet) souvent rapporté dans cette littérature – notamment contre les lois platikurtiques – et permettent des gains sensibles de puissance par rapport aux méthodes combinées usuelles.
Abstract
This paper illustrates the usefulness of resampling-based methods in the context of multiple (simultaneous) tests, with emphasis on econometric applications. Economic theory often suggests joint (or simultaneous) hypotheses on econometric models; consequently, the problem of evaluating joint rejection probabilities arises frequently in econometrics and statistics. In this regard, it is well known that ignoring the joint nature of multiple hypotheses may lead to serious test size distortions. Whereas most available multiple test techniques are conservative in the presence of non-independent statistics, our proposed tests provably achieve size control. Specifically, we use the Monte-Carlo (MC) test technique to extend several well known combination methods to the non-independent statistics contexts. We first cast the multiple test problem into a unified statistical framework which: (i) serves to show how exact global size control is achieved through the MC test method, and (ii) yields a number of superior tests previously not considered. Secondly, we provide a review of relevant available results. Finally, we illustrate the applicability of our proposed procedure to the problem of moments-based normality tests. For this problem, we propose an exact variant of Kiefer and Salmon’s (1983) test, and an alternative combination method which exploits the well known Fisher-Pearson procedure. Our simulation study reveals that the latter method seems to correct for the problem of test biases against platikurtic alternatives. In general, our results show that concrete and non-spurious power gains (over standard combination methods) can be achieved through our multiple Monte-Carlo test approach.
Appendices
Bibliographie
-
Andrews, D. W. K. (1993), « Tests for Parameter Instability and Structural Change with Unknown Change Point », Econometrica, 61 : 821-856.10.2307/2951764 Google Scholar Search this bibliographic reference on Google Scholar
-
Andrews, D. W. K. et W. Ploberger (1994), « Optimal Tests when a Nuisance Parameter is Present only under the Alternative », Econometrica, 62 : 1 383-1 414.10.1016/0304-4076(82)90103-8 Google Scholar Search this bibliographic reference on Google Scholar
-
Barnard, G. A. (1963), « Comment on ‘The Spectral Analysis of Point Processes’ by M. S. Bartlett », Journal of the Royal Statistical Society, Series B, 25 : 294.10.1016/j.jeconom.2004.02.014 Google Scholar Search this bibliographic reference on Google Scholar
-
Bera, A. K. et C. M. Jarque (1982), « Model Specification Tests: A Simultaneous Approach », Journal of Econometrics, 20 : 59-82.10.1016/0304-4076(82)90103-8 Google Scholar Search this bibliographic reference on Google Scholar
-
Bewley, R. et H. Theil (1987), « Monte-Carlo Testing for Heteroscedasticity in Equation Systems », Advances in Econometrics, 6 : 1-15.10.2307/1912558 Google Scholar Search this bibliographic reference on Google Scholar
-
Bontemps, C. et N. Meddahi (2005), « Testing Normality: A GMM Approach », Journal of Econometrics, 124 : 149-186.10.1016/j.jeconom.2004.02.014 Google Scholar Search this bibliographic reference on Google Scholar
-
Bowman, K. O. et B. R. Shenton (1975), « Omnibus Test Contours for Departures from Normality Based on
and b2 », Biometrika, 52 : 591-611.10.1111/1540-5982.t01-3-00001 Google Scholar Search this bibliographic reference on Google Scholar -
Box, G. E. P. et D. A. Pierce (1970), « Distribution of Residual Autocorrelations in Autoregressive-integrated Moving Average Time Series Models », Journal of the American Statistical Association, 65 : 1 509-1 526.10.1111/1368-423X.11009 Google Scholar Search this bibliographic reference on Google Scholar
-
Campbell, Y. Y., A. W. Lo et A. C. MacKinlay (1997), The Econometrics of Financial Markets, Princeton University Press, New Jersey.10.1016/S0304-4076(01)00093-8 Google Scholar Search this bibliographic reference on Google Scholar
-
Chernick, M. R. (1999), Bootstrap Methods: A Practitioner’s Guide, John Wiley & Sons, New York.10.1016/S0304-4076(02)00108-2 Google Scholar Search this bibliographic reference on Google Scholar
-
Christiano, L. J. (1992), « Searching for a Break in GNP », Journal of Business and Economic Statistics, 10 : 237-249.10.1046/j.0305-9049.2003.00085.x Google Scholar Search this bibliographic reference on Google Scholar
-
D’Agostino, R. B. et M. A. Stephens (éds) (1986), Goodness-of-Fit Techniques, Marcel Dekker, New York.10.1016/j.jeconom.2003.10.024 Google Scholar Search this bibliographic reference on Google Scholar
-
Davison, A. et D. Hinkley (1997), Bootstrap Methods and Their Application, Cambridge University Press, Cambridge (UK).10.1016/0304-4076(94)01683-6 Google Scholar Search this bibliographic reference on Google Scholar
-
Deschamps, P. (1996), « Monte-Carlo Methodology for LM and LR Autocorrelation Tests in Multivariate Regressions », Annales d’Économie et de Statistique, 43 : 150-169.10.1214/aoms/1177707045 Google Scholar Search this bibliographic reference on Google Scholar
-
Diebold, F. X. et C. Chen (1996), « Testing Structural Stability with Endogenous Break Point: A Size Comparison of Analytic and Bootstrap Procedures », Journal of Econometrics, 70 : 221-241.10.1016/0304-4076(94)01690-9 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. (1989), « Nonlinear Hypotheses, Inequality Restrictions, and Non-nested Hypotheses: Exact Simultaneous Tests in Linear Regressions », Econometrica, 57 : 335-355.10.2307/1912558 Google Scholar Search this bibliographic reference on Google Scholar
- Dufour, J.-M. (2001), « Logique et tests d’hypothèses : réflexions sur les problèmes mal posés en économétrie », L’Actualité économique, 77(2) : 171-190.
10.7202/602348ar Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. (2002), « Monte-Carlo Tests with Nuisance Parameters: A General Approach to Finite-sample Inference and Nonstandard Asymptotics in Econometrics », Journal of Econometrics, à paraître.10.2307/1403192 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. (2003), « Identification, Weak Instruments and Statistical Inference in Econometrics », Canadian Journal of Economics, 36(4) : 767-808.10.1111/1540-5982.t01-3-00001 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et A. Farhat (2001), « Exact Nonparametric Two-sample Homogeneity Tests for Possibly Discrete Distributions », Technical report, C.R.D.E., Université de Montréal, 26 pages.10.1037/h0059111 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M., A. Farhat, L. Gardiol et L. Khalaf (1998), « Simulation-based Finite Sample Normality Tests in Linear Regressions », The Econometrics Journal, 1 : 154-173.10.1111/1368-423X.11009 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et L. Khalaf (2001), « Monte-Carlo Test Methods in Econometrics », in B. Baltagi (éd.), Companion to Theoretical Econometrics, Blackwell Companions to Contemporary Economics, Basil Blackwell, Oxford, U.K., chapter 23, p. 494-519.10.1111/j.2517-6161.1963.tb00508.x Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et L. Khalaf (2002a), « Exact Simulation Based Muliple Hypothesis Tests », Technical report, CIRANO et CIREQ, Université de Montréal et Département d’économique, Université Laval.Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et L. Khalaf (2002b), « Exact Tests for Contemporaneous Correlation of Disturbances in Seemingly Unrelated Regressions », Journal of Econometrics, 106(1) : 143-170.10.1016/S0304-4076(01)00093-8 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et L. Khalaf (2002c), « Simulation Based Finite and Large Sample Tests in Multivariate Regressions », Journal of Econometrics, 111(2) : 303-322.10.1016/S0304-4076(02)00108-2 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M., L. Khalaf et M.-C. Beaulieu (2002), « Finite-sample Diagnostics for Multivariate Regressions with Applications to Linear Asset Pricing Models », Technical report, CIRANO et CIREQ, Université de Montréal et Département d’économique, Université Laval.10.1515/9781400830213 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M., L. Khalaf et M.-C. Beaulieu (2003), « Exact Skewness-kurtosis Tests for Multivariate Normality and Goodness-of-fit in Multivariate Regressions with Application to Asset Pricing Models », Oxford Bulletin of Economics and Statistics, 65 : 891-906.10.1046/j.0305-9049.2003.00085.x Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M., L. Khalaf, J.-T. Bernard et I. Genest (2004), « Simulation-based Finite-sample Tests for Heteroskedasticity and ARCH Effects », Journal of Econometrics, 122 : 319-347.10.1016/j.jeconom.2003.10.024 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et J. F. Kiviet (1996), « Exact Tests for Structural Change in First-order Dynamic Models », Journal of Econometrics, 70 : 39-68.10.1016/0304-4076(94)01683-6 Google Scholar Search this bibliographic reference on Google Scholar
-
Dufour, J.-M. et O. Torrès (1998), « Union-intersection and Sample-split Methods in Econometrics with Applications to SURE and MA Models », in D. E. A. Giles et A. Ullah (éds), Handbook of Applied Economic Statistics, Marcel Dekker, New York, p. 465-505.10.1017/CBO9780511802843 Google Scholar Search this bibliographic reference on Google Scholar
-
Dwass, M. (1957), « Modified Randomization Tests for Nonparametric Hypotheses », Annals of Mathematical Statistics, 28 : 181-187.10.1214/aoms/1177707045 Google Scholar Search this bibliographic reference on Google Scholar
-
Efron, B. et R. J. Tibshirani (1993), An Introduction to the Bootstrap, vol. 57, Monographs on Statistics and Applied Probability, Chapman & Hall, New York.Google Scholar Search this bibliographic reference on Google Scholar
-
Fisher, R. A. (1930), « The Moments of the Distribution for Normal Samples of Measures for Departures from Normality », Proceedings of the Royal Society of London A, 130 : 16-28.10.1098/rspa.1930.0185 Google Scholar Search this bibliographic reference on Google Scholar
-
Fisher, R. A. (1932), Statistical Methods for Research Workers, Oliver and Boyd, Edinburgh.10.1002/9780470996249.ch24 Google Scholar Search this bibliographic reference on Google Scholar
-
Folks, J. L. (1984), « Combination of Independent Tests », in P. R. Krishnaiah et P. K. Sen (éds), Handbook of Statistics 4: Nonparametric Methods, North-Holland, Amsterdam, p. 113-121.Google Scholar Search this bibliographic reference on Google Scholar
-
Fong, M. F., S. K. Koh et S. Ouliaris (1997), « Joint Variance-ratio Tests of the Martingale Hypothesis for Exchange Rates », Journal of Business and Economic Statistics, 15 : 51-59.Google Scholar Search this bibliographic reference on Google Scholar
-
Goldfeld, S. M. et R. Quandt (1965), « Some Tests for Heteroscedasticity », Journal of the American Statistical Association, 60 : 539-547.Google Scholar Search this bibliographic reference on Google Scholar
-
Good, I. J. (1955), « On the Weighted Combination of Significance Tests », Journal of the Royal Statistical Society, Series B, 17 : 264-265.10.1007/978-1-4899-4541-9 Google Scholar Search this bibliographic reference on Google Scholar
-
Hall, P. (1992), The Bootstrap and Edgeworth Expansion, Springer-Verlag, New York.Google Scholar Search this bibliographic reference on Google Scholar
-
Harvey, A. C. et G. D. A. Phillips (1980), « Testing for Serial Correlation in Simultaneous Equation Models », Econometrica, 48 : 747-759.10.2307/1913133 Google Scholar Search this bibliographic reference on Google Scholar
-
Horowitz, J. L. (1997), « Bootstrap Methods in Econometrics: Theory and Numerical Performance », in D. Kreps et K.W. Wallis (éds), Advances in Economics and Econometrics, vol. 3, Cambridge University Press, Cambridge, U.K., p. 188-222.10.1080/07350015.1997.10524686 Google Scholar Search this bibliographic reference on Google Scholar
-
Jarque, C. M. et A. K. Bera (1980), « Efficient Tests for Normality, Heteroscedasticity and Serial Independence of Regression Residuals », Economics Letters, 6 : 255-259.10.1016/0165-1765(80)90024-5 Google Scholar Search this bibliographic reference on Google Scholar
-
Jarque, C. M. et A. K. Bera (1987), « A Test for Normality of Observations and Regression Residuals », International Statistical Review, 55 : 163-172.10.2307/1403192 Google Scholar Search this bibliographic reference on Google Scholar
-
Kiefer, N. M. et M. Salmon (1983), « Testing Normality in Econometric Models », Economic Letters, 11 : 123-127.10.1016/0165-1765(83)90172-6 Google Scholar Search this bibliographic reference on Google Scholar
-
Kilian, L. et U. Demiroglu (2000), « Residual-based Tests for Normality in Autoregressions: Asymptotic Theory and Simulation Evidence », Journal of Business and Economic Statistics, 18 : 40-50.10.1017/CBO9781139051996.007 Google Scholar Search this bibliographic reference on Google Scholar
-
Mardia, K. V. (1980), « Tests of Univariate and Multivariate Normality », in P. R. Krishnaiah (éd.), Handbook of Statistics 1: Analysis of Variance, North-Holland, Amsterdam, p. 279-320.10.1080/07350015.2000.10524846 Google Scholar Search this bibliographic reference on Google Scholar
-
Miller, Jr., R. G. (1981), Simultaneous Statistical Inference, 2e éd., Springer-Verlag, New York.10.1016/S0169-7161(80)01011-5 Google Scholar Search this bibliographic reference on Google Scholar
-
Pearson, K. (1933), « On a Method of Determining Whether a Sample of Size n Supposed to Have Been Drawn from a Parent Population », Biometrika, 25 : 379-410.10.1007/978-1-4613-8122-8 Google Scholar Search this bibliographic reference on Google Scholar
-
Savin, N. E. (1984), « Multiple Hypothesis Testing », in Z. Griliches et M. D. Intrilligator (éds), Handbook of Econometrics, Volume 2, North-Holland, Amsterdam, chap. 14, p. 827-879.10.1093/biomet/25.3-4.379 Google Scholar Search this bibliographic reference on Google Scholar
-
Thode, H. C. Jr., (2002), Testing for Normality, number 164 in Statistics: Textbooks and Monographs, Marcel Dekker, New York.10.1016/S1573-4412(84)02006-7 Google Scholar Search this bibliographic reference on Google Scholar
-
Tippett, L. H. (1931), The Methods of Statistics, Williams and Norgate, London.Google Scholar Search this bibliographic reference on Google Scholar
-
Westfall, P. H. et S. S. Young (1993), Resampling-Based Multiple Testing: Examples and Methods for p-Value Adjustment, John Wiley & Sons, New York.Google Scholar Search this bibliographic reference on Google Scholar
-
White, H. (2000), « A Reality Check for Data Snooping », Econometrica, 68 : 1 097-1 126.Google Scholar Search this bibliographic reference on Google Scholar
-
Wilkinson, B. (1951), « A Statistical Consideration in Psychological Research », Psychology Bulletin, 48 : 156-158.10.1037/h0059111 Google Scholar Search this bibliographic reference on Google Scholar
-
Zhou, G. (1993), « Asset-pricing Tests Under Alternative Distributions », The Journal of Finance, 48 : 1 927-1 942.10.1111/j.1540-6261.1993.tb05134.x Google Scholar Search this bibliographic reference on Google Scholar
