×

Bootstrap inference on the boundary of the parameter space, with application to conditional volatility models. (English) Zbl 07491158

Summary: It is a well-established fact that – with an unknown number of nuisance parameters at the boundary – testing a null hypothesis on the boundary of the parameter space is infeasible in practice as the limiting distributions of standard test statistics are non-pivotal. In particular, likelihood ratio statistics have limiting distributions which can be characterized in terms of quadratic forms minimized over cones, where the shape of the cones depends on the unknown location of the (possibly multiple) model parameters not restricted by the null hypothesis. We propose to solve this inference problem by a novel bootstrap, which we show to be valid under general conditions, irrespective of the presence of (unknown) nuisance parameters on the boundary. That is, the new bootstrap replicates the unknown limiting distribution of the likelihood ratio statistic under the null hypothesis and is bounded (in probability) under the alternative. The new bootstrap approach, which is very simple to implement, is based on shrinkage of the parameter estimates used to generate the bootstrap sample toward the boundary of the parameter space at an appropriate rate. As an application of our general theory, we treat the problem of inference in finite-order ARCH models with coefficients subject to inequality constraints. Extensive Monte Carlo simulations illustrate that the proposed bootstrap has attractive finite sample properties both under the null and under the alternative hypothesis.

MSC:

62-XX Statistics
91-XX Game theory, economics, finance, and other social and behavioral sciences

References:

[1] Agosto, A.; Cavaliere, G.; Kristensen, D.; Rahbek, A., Modeling corporate defaults: Poisson autoregressions with exogenous covariates (PARX), J. Empir. Financ., 38, B, 640-663 (2016)
[2] Andrews, D. W.K., Estimation when a Parameter is on a Boundary, Econometrica, 67, 6, 1341-1383 (1999) · Zbl 1056.62507
[3] Andrews, D. W.K., Inconsistency of the Bootstrap when a Parameter is on the Boundary of the Parameter Space, Econometrica, 68, 2, 399-405 (2000) · Zbl 1015.62044
[4] Andrews, D. W.K., Testing when a Parameter is on the Boundary of the Maintained Hypothesis, Econometrica, 69, 3, 683-734 (2001) · Zbl 0999.62010
[5] Andrews, D. W.K.; Guggenberger, P., Hybrid and Size-corrected Subsampling Methods, Econometrica, 77, 3, 721-762 (2009) · Zbl 1176.62117
[6] Beran, R., Diagnosing Bootstrap Success, Ann. Inst. Statist. Math., 49, 1-24 (1997) · Zbl 0928.62035
[7] Beutner, E.; Heinemann, A.; Smeekes, S., A Residual Bootstrap for Conditional Value-at-Risk (2018), arXiv:1808.09125
[8] Bickel, P. J.; Klaassen, C. A.J.; Ritov, Y.; Wellner, J. A., Efficient and Adaptive Estimation for Semiparametric Models (1998), Springer: Springer New York · Zbl 0894.62005
[9] Cavaliere, G.; Nielsen, H. B.; Rahbek, A., Bootstrap Testing of Hypotheses on Co-Integration Relations in Vector Autoregressive Models, Econometrica, 83, 2, 813-831 (2015) · Zbl 1410.62040
[10] Cavaliere, G.; Nielsen, H. B.; Rahbek, A., On the consistency of Bootstrap testing for a parameter on the Boundary of the Parameter Space, J. Time Series Anal., 38, 513-534 (2017) · Zbl 1416.62480
[11] Cavaliere, G.; Pedersen, R. S.; Rahbek, A., The fixed volatility Bootstrap for a Class of ARCH \((q)\) Models, J. Time Series Anal., 39, 920-941 (2018) · Zbl 1402.62196
[12] Cavaliere, G.; Rahbek, A.; Taylor, A. M.R., Bootstrap Determination of the Co-Integration Rank in Vector Autoregressive Models, Econometrica, 80, 1721-1740 (2012) · Zbl 1274.62223
[13] Chernoff, H., On the Distribution of the Likelihood Ratio, Ann. Math. Stat., 54, 573-578 (1954) · Zbl 0056.37102
[14] Chernozhukov, V.; Hong, H.; Tamer, E., Estimation and confidence regions for Parameter sets in Econometric Models, Econometrica, 75, 1243-1284 (2007) · Zbl 1133.91032
[15] Corradi, V.; Iglesias, E. M., Bootstrap Refinements for QML Estimators of the GARCH(1, 1) Parameters, J. Econometrics, 144, 500-510 (2008) · Zbl 1418.62313
[16] Corsi, F., A Simple Approximate Long-Memory Model of Realized Volatility, J. Financ. Econom., 7, 174-196 (2009)
[17] Davidson, R.; Flachaire, E., The Wild Bootstrap, Tamed at Last, J. Econometrics, 146, 162-169 (2008) · Zbl 1418.62183
[18] Davidson, R.; MacKinnon, J., The power of Bootstrap and Asymptotic Tests, J. Econometrics, 133, 421-441 (2006) · Zbl 1345.62058
[19] Demos, A.; Sentana, E., Testing for GARCH effects: A one-sided Approach, J. Econometrics, 86, 97-127 (1998) · Zbl 0962.62083
[20] Doornik, J., Object Oriented Matrix Programming using Ox (2007), Timberlake Consultants Press: Timberlake Consultants Press London
[21] Elliott, G.; Müller, U.; Watson, M., Nearly Optimal Tests When a Nuisance Parameter Is Present Under the Null Hypothesis, Econometrica, 83, 2, 771-811 (2015) · Zbl 1410.62029
[22] Francq, C.; Zakoïan, J. M., Quasi-Maximum Likelihood Estimation in GARCH Processes when some Coefficients are equal to Zero, Stochastic Process. Appl., 117, 9, 1165-1372 (2007)
[23] Francq, C.; Zakoïan, J. M., Testing the Nullity of GARCH Coefficients: Correction of the Standard Tests and Relative Efficiency Comparisons, J. Amer. Statist. Assoc., 104, 313-324 (2009) · Zbl 1388.62252
[24] Francq, C.; Zakoïan, J. M., QML Estimation of a Class of Multivariate Asymmetric GARCH Models, Econometric Theory, 28, 179-206 (2012) · Zbl 1234.62120
[25] Hall, P., The Bootstrap and Edgeworth Expansion (1992), Springer: Springer Berlin · Zbl 0744.62026
[26] Hall, P.; Yao, Q., Inference in ARCH and GARCH Models with Heavy-Tailed Errors, Econometrica, 71, 285-317 (2003) · Zbl 1136.62368
[27] Hidalgo, J.; Zaffaroni, P., A Goodness-of-Fit Test for ARCH \(\left( \infty\right)\) Models, J. Econometrics, 141, 973-1013 (2007) · Zbl 1420.62385
[28] Horowitz, J., The bootstrap, (Heckman, J. J.; Leamer, E., Handbook of Econometrics, Vol. 5 (2001)), 3159-3228, ch. 52 · Zbl 0986.62102
[29] Jeantheau, T., Strong Consistency of Estimators for Multivariate ARCH Models, Econometric Theory, 14, 70-86 (1998)
[30] Jensen, S. T.; Rahbek, A., Asympotic Inference for Non-Stationary GARCH, Econometric Theory, 30, 1203-1226 (2004) · Zbl 1069.62067
[31] Jeong, M., Residual-based GARCH Bootstrap and Second Order Asymptotic Refinement, Econometric Theory, 33, 779-790 (2017) · Zbl 1392.62265
[32] Ketz, P., Subvector Inference when the True Parameter Vector may be Near or at the Boundary, J. Econometrics, 207, 285-306 (2018) · Zbl 1452.62930
[33] Kopylev, L.; Sinha, B., On the Asymptotic Distribution of Likelihood Ratio Test when Parameters Lie on the BoundaryTechnical Report (2010), Department of Mathematics and Statistics, UMBC
[34] Kopylev, L.; Sinha, B., On the asymptotic distribution of likelihood ratio test when parameters lie on the Boundary, Sankhyā B, 73, 20-41 (2011) · Zbl 1230.62021
[35] Ling, S.; McAleer, M., Asymptotic Theory for a Vector ARMA-GARCH Model, Econometric Theory, 19, 280-310 (2003) · Zbl 1441.62799
[36] Lu, Z., Extended MaxT Tests of One-Sided Hypotheses, J. Amer. Statist. Assoc., 111, 423-437 (2016)
[37] McCloskey, A., Bonferroni-based Size-Correction for Nonstandard Testing Problems, J. Econometrics, 200, 17-35 (2017) · Zbl 1388.62371
[38] Pedersen, R. S., Inference and Testing on the Boundary in Extended Constant Conditional Correlation GARCH Models, J. Econometrics, 196, 23-36 (2017) · Zbl 1443.62282
[39] Pedersen, R. S.; Rahbek, A., Testing GARCH-X Type models, Econometric Theory, 35, 1012-1047 (2019) · Zbl 1432.62310
[40] Silvapulle, M. J.; Sen, P. K., Constrained Statistical Inference: Inequality, Order, and Shape Restrictions (2005), John Wiley & Sons: John Wiley & Sons New York · Zbl 1077.62019
[41] Swensen, A. R., Bootstrap Algorithms for Testing and Determining the Co-Integration Rank in VAR Models, Econometrica, 74, 1699-1714 (2006) · Zbl 1187.62148
[42] Tsay, R. S., Conditional Heteroscedastic Time Series Models, J. Amer. Statist. Assoc., 82, 590-604 (1987) · Zbl 0636.62092
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.