Startseite Bootstrap LM Tests for Spatial Dependence in Panel Data Models with Fixed Effects
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

Bootstrap LM Tests for Spatial Dependence in Panel Data Models with Fixed Effects

  • Bianling Ou EMAIL logo , Zhihe Long und Wenqian Li
Veröffentlicht/Copyright: 18. September 2019
Veröffentlichen auch Sie bei De Gruyter Brill

Abstract

This paper applies bootstrap methods to LM tests (including LM-lag test and LM-error test) for spatial dependence in panel data models with fixed effects, and removes fixed effects based on orthogonal transformation method proposed by Lee and Yu (2010). The consistencies of LM tests and their bootstrap versions are proved, and then some asymptotic refinements of bootstrap LM tests are obtained. It shows that the convergence rate of bootstrap LM tests is O((NT)−2) and that of fast double bootstrap LM tests is O((NT)−5/2). Extensive Monte Carlo experiments suggest that, compared to aysmptotic LM tests, the size of bootstrap LM tests gets closer to the nominal level of signifiance, and the power of bootstrap LM tests is higher, especially in the cases with small spatial correlation. Moreover, when the error is not normal or with heteroskedastic, asymptotic LM tests suffer from severe size distortion, but the size of bootstrap LM tests is close to the nominal significance level. Bootstrap LM tests are superior to aysmptotic LM tests in terms of size and power.


supported by the National Natural Science Foundation of China (71271088), Beijing Municipal Social Science Foundation (15JGB072) and Humanity and Social Science Youth Foundation of Ministry of Education of China (15YJCZH122)


References

[1] Horowitz J L. The bootstrap. Eds. by Heckman J J and Leamer E. Handbook of Econometrics, Elsevier Science B V, 2001.10.1016/S1573-4412(01)05005-XSuche in Google Scholar

[2] Beran R. Prepivoting test statistics: A bootstrap view of asymptotic refinements. Journal of the American Statistical Association, 1988, 83: 687–697.10.1080/01621459.1988.10478649Suche in Google Scholar

[3] Hall P. The bootstrap and edgeworth expansion. Springer-Verlag, 1992.10.1007/978-1-4612-4384-7Suche in Google Scholar

[4] Horowitz J L. Bootstrap-based critical values for the information matrix test. Journal of Econometrics, 1994, 61: 395–411.10.1016/0304-4076(94)90092-2Suche in Google Scholar

[5] Horowitz J L. Bootstrap methods in econometrics: Theory and numericalperformance. Eds. by Kreps D M, Wallis K F. Advances in Economics andEconometrics: Theory and Applications: Seventh World Congress. CambridgeUniversity Press, Cambridge, 1997.Suche in Google Scholar

[6] Hall P, Horowitz J L. Bootstrap critical values for tests based on generalizedmethodsof moments estimators. Econometrica, 1996, 4: 891–916.10.2307/2171849Suche in Google Scholar

[7] Cameron A C, Trivedi P K. Microeconometrics methods and applications. Cambridge University Press, 2005.10.1017/CBO9780511811241Suche in Google Scholar

[8] Godfrey L. Bootstrap tests for regression models. Palgrave Macmillan, 2009.10.1057/9780230233737Suche in Google Scholar

[9] Davidson, MacKinnon J G. The size distortion of bootstrap tests. Econometric Theory, 1999, 15: 361–376.10.1017/S0266466699153040Suche in Google Scholar

[10] Davidson R, MacKinnon J G. The power of bootstrap and asymptotic tests. Journal of Econometrics, 2006, 133: 421–441.10.1016/j.jeconom.2005.06.002Suche in Google Scholar

[11] Davidson R, MacKinnon J G. Fast double bootstrap tests of nonnested linear regression models. Econometric Reviews, 2002, 21: 419–429.10.1081/ETC-120015384Suche in Google Scholar

[12] Lin K P, Long Z H, Ou B L. The size and power of bootstrap tests for spatialdependence in a linear regression model. Computational Economics, 2011, 38: 153–171.10.1007/s10614-010-9224-0Suche in Google Scholar

[13] Long Z H, Ou B L, Lin K P. Tests for patial dependence applying bootstrap methods: Mathematics derivation and simulation analysis. Beijing: Science Press, 2012, (in Chinese).Suche in Google Scholar

[14] Ou B L, Long Z H, Lin K P. Size distortion of bootstrap Moran diagnostic testing for spatial autoregressive models. Systems Engineering, 2009, 27(8): 69–73 (in Chinese).Suche in Google Scholar

[15] Anselin L. Spatial econometrics: Methods and models. Kluwar Academic Publishing, 1998.Suche in Google Scholar

[16] Anselin L. Some robust approaches to testing and estimation in spatial econometrics. Regional Science Urban Economics, 1990, 20: 141–163.10.1016/0166-0462(90)90001-JSuche in Google Scholar

[17] Burridge P, Fingleton B. Bootstrap inference in spatial econometrics: The J-test. Spatial Economic Analysis, 2010, 5: 93–119.10.1080/17421770903511346Suche in Google Scholar

[18] Fingleton B, Palombi S. Bootstrap J-test for panel data models with spatially dependent error components, a spatial lag and additional endogenous variables. Spatial Economic Analysis, 2015, 11(1): 1–20.10.1080/17421772.2014.1000024Suche in Google Scholar

[19] Su L J, Yang Z L. Asymptotics and bootstrap for transformed panel data regressions. Working paper, 2009.Suche in Google Scholar

[20] Yang Z L. LM tests of spatial dependence based on bootstrap critical values. Journal of Econometrics, 2015, 185: 33–59.10.1016/j.jeconom.2014.10.005Suche in Google Scholar

[21] Monchuk D C, Hayes D J, Miranowski J A, et al. Inference basedon alternative bootstrapping methods in spatial models with an application tocounty income growth in the United States. Journal of Regional Science, 2011, 51: 880–896.10.1111/j.1467-9787.2011.00716.xSuche in Google Scholar

[22] Anselin L, Bera A K, Florax R, et al. Simple diagnostic tests for spatial dependence. Regional Science Urban Economics, 1996, 26: 77–104.10.1016/0166-0462(95)02111-6Suche in Google Scholar

[23] Kelejian H H, Robinson D P. A suggested test for spatial autocorrelation and/or heteroskedasticity and corresponding Monte Carlo results. Regional Science and Urban Economics, 1998, 28(4): 389–417.10.1016/S0166-0462(98)00007-6Suche in Google Scholar

[24] Debarsy N, Ertur C. Testing for spatial autocorrelation in a fixed effects panel data model. Regional Science and Urban Economics, 2010, 40: 453–470.10.1016/j.regsciurbeco.2010.06.001Suche in Google Scholar

[25] Long Z H, Li W L, Chen Q Q. Bootstrap {\rm LM-error} test of spatial correlation in fixed effects model. The Journal of Quantitative and Technical Economics, 2015, 8: 149–160 (in Chinese).Suche in Google Scholar

[26] Ren T X, Long Z H, Chen Q Q. LM-Error test of spatial panel data model based on bootstrap method. Statistical Research, 2015, 32(5): 91–96 (in Chinese).Suche in Google Scholar

[27] Jin F, Lee L F. On the bootstrap for Moran's I test for spatial dependence. Journal of Econometrics, 2015, 184: 295–314.10.1016/j.jeconom.2014.09.005Suche in Google Scholar

[28] Elhorst J P. Spatial panel data models. Eds. by Fischer M M, Getis A. Handbook of Applied Spatial Analysis, Springer: Berlin Heidelberg, New York, 2010.10.1007/978-3-642-03647-7_19Suche in Google Scholar

[29] Anselin L, et al. Spatial panel econometrics. Eds. by Matyas L, Sevestre P. The Econometrics of panel data, Springer-Verlag, 2008.10.1007/978-3-540-75892-1_19Suche in Google Scholar

[30] Burridge P. On the Cliff-Ord test for spatial autocorrelation. Journal of the Royal Statistical Society B, 1980, 42: 107–108.10.1111/j.2517-6161.1980.tb01108.xSuche in Google Scholar

[31] Lee L F, Yu J H. Estimation of spatial autoregressive panel data models with fixed effects. Journal of Econometrics, 2010, 154: 165–185.10.1016/j.jeconom.2009.08.001Suche in Google Scholar

[32] Ahlgren N, Antell J. Bootstrap and fast double bootstrap tests for cointegration rank with financial time series. Computational Statistics and Data Analysis, 2008, 52: 4754–4767.10.1016/j.csda.2008.03.025Suche in Google Scholar

[33] Arasan J, Adam M B. Double bootstrap confidence interval estimates with censored and truncated data. Journal of Modem Applied Statistical Methods, 2014, 13: 399–419.10.22237/jmasm/1414815660Suche in Google Scholar

[34] Davidson R, MacKinnon J G. Improving the reliability of bootstrap tests with the fast double bootstrap. Computational Statistics and Data Analysis, 2007, 51: 3259–3281.10.1016/j.csda.2006.04.001Suche in Google Scholar

[35] Davidson R, MacKinnon J G. Diagnostics for the bootstrap and fast double bootstrap. Econometric Reviews, 2017, 36: 6–9.10.1080/07474938.2017.1307918Suche in Google Scholar

[36] Kelejian H H, Prucha I R. On the asymptotic distribution of the Moran I teststatistic with applications. Journal of Econometrics, 2001, 104: 219–257.10.1016/S0304-4076(01)00064-1Suche in Google Scholar

[37] Lee L F, Yu J H. Estimation of spatial panels. Foundations and Trends in Econometrics, 2011, 4(1–2): 1–164.10.1561/0800000015Suche in Google Scholar

[38] Lee L F, Yu J H. Spatial panels: Random components versus fixed effects. International Economic Review, 2012, 53: 1369–1412.10.1111/j.1468-2354.2012.00724.xSuche in Google Scholar

[39] Mammen E. When does bootstrap work? Asymptotic results and simulations. Springer-Verlag, 1992.10.1007/978-1-4612-2950-6Suche in Google Scholar

[40] Kelejian H H, Prucha I R. A generalized moments estimator for the autoregressive parameter in a spatial model. Internaltional Economic Review, 1999, 40(2): 509–533.10.1111/1468-2354.00027Suche in Google Scholar

Received: 2016-12-26
Accepted: 2017-12-07
Published Online: 2019-09-18
Published in Print: 2019-09-25

© 2019 Walter De Gruyter GmbH, Berlin/Boston

Heruntergeladen am 20.11.2025 von https://www.degruyterbrill.com/document/doi/10.21078/JSSI-2019-330-14/html
Button zum nach oben scrollen