New Approaches for Testing Slope Homogeneity in Large Panel Data Models

Abstract

Testing slope homogeneity is important in panel data modeling. Existing approaches typically take the summation over a sequence of test statistics that measure the heterogeneity of individual panels; they are referred to as Sum tests. We propose two procedures for slope homogeneity testing in large panel data models. One is called a Max test that takes the maximum over these individual test statistics. The other is referred to as a Combo test, which combines a certain Sum test (i.e., that of Pesaran and Yamagata in J Econom 142:50-93, 2008) and the proposed Max test together. We derive the limiting null distributions of the two test statistics, respectively, when both the number of individuals and temporal observations jointly diverge to infinity, and demonstrate that the Max test is asymptotically independent of the Sum test. Numerical results show that the proposed approaches perform satisfactorily.

Keywords

Asymptotic independence / Large panels / Panel data models / Slope homogeneity

References

[1] Ando T, Bai J. A simple new test for slope homogeneity in panel data models with interactive effects. Econom. Lett.. 2015, 136 112-117

[2] Bai J. Panel data models with interactive fixed effects. Econometrica. 2009, 77 4 1229-1279

[3] Blomquist J, Westerlund J. Testing slope homogeneity in large panels with serial correlation. Econom. Lett.. 2013, 121 3 374-378

[4] Breitung J, Roling C, Salish N. Lagrange multiplier type tests for slope homogeneity in panel data models. Econom. J.. 2016, 19 2 166-202

[5] Breusch TS, Pagan AR. A simple test for heteroscedasticity and random coefficient variation. Econometrica. 1979, 47 5 1287-1294

[6] Cai TT, Liu W, Xia Y. Two-sample test of high dimensional means under dependence. J. R Stat. Soc. Ser. B Stat. Methodol.. 2014, 76 2 349-372

[7] Chow, T.L., Teugels, J.L.: The sum and the maximum of iid random variables. In: Proceedings of the 2nd Prague Symposium on Asymptotic Statistics, vol 45, pp 394–403 (1978)

[8] Embrechts, P., Klüppelberg, C., Mikosch, T.: Modelling extremal events: for insurance and finance, vol 33. Springer Science & Business Media (2013)

[9] Fama EF, French KR. Common risk factors in the returns on stocks and bonds. J. Financ. Econ.. 1993, 33 1 3-56

[10] Feng L, Jiang T, Liu B, Xiong W. Max-sum tests for cross-sectional independence of high-dimensional panel data. Ann. Statist.. 2022, 50 2 1124-1143

[11] Hausman JA. Specification tests in econometrics. Econometrica. 1978, 46 6 1251-1271

[12] Hsing T. A note on the asymptotic independence of the sum and maximum of strongly mixing stationary random variables. Ann. Probab.. 1995, 23 2 938-947

[13] Juhl T, Lugovskyy O. A test for slope heterogeneity in fixed effects models. Econom. Rev.. 2014, 33 8 906-935

[14] Laurent B, Massart P. Adaptive estimation of a quadratic functional by model selection. Ann. Statist.. 2000, 28 5 1302-1338

[15] Li, D., Xue, L.: Joint limiting laws for high-dimensional independence tests. arXiv preprint arXiv:1512.08819 (2015)

[16] Liu WD, Lin Z, Shao QM. The asymptotic distribution and Berry-Esseen bound of a new test for independence in high dimension with an application to stochastic optimization. Ann. Appl. Probab.. 2008, 18 6 2337-2366

[17] Pesaran, H., Smith, R., Im, K.S.: Dynamic linear models for heterogenous panels. In: The Econometrics of Panel Data, Springer, pp 145–195 (1996)

[18] Pesaran MH, Yamagata T. Testing slope homogeneity in large panels. J Econom.. 2008, 142 1 50-93

[19] Phillips PCB, Sul D. Dynamic panel estimation and homogeneity testing under cross section dependence. Econom. J.. 2003, 6 1 217-259

[20] Swamay PAVB. Efficient inference in a random coefficient regression model. Econometrica. 1970, 38 311-323

[21] Wang HJ, McKeague IW, Qian M. Testing for marginal linear effects in quantile regression. J. R Stat. Soc. Ser. B Stat. Methodol.. 2018, 80 2 433-452

[22] Zellner A. An efficient method of estimating seemingly unrelated regressions and tests for aggregation bias. J. Amer. Statist. Assoc.. 1962, 57 348-368