Abstract
For checking on heteroscedasticity in regression models, a unified approach is proposed to constructing test statistics in parametric and nonparametric regression models. For nonparametric regression, the test is not affected sensitively by the choice of smoothing parameters which are involved in estimation of the nonparametric regression function. The limiting null distribution of the test statistic remains the same in a wide range of the smoothing parameters. When the covariate is one-dimensional, the tests are, under some conditions, asymptotically distribution-free. In the high-dimensional cases, the validity of bootstrap approximations is investigated. It is shown that a variant of the wild bootstrap is consistent while the classical bootstrap is not in the general case, but is applicable if some extra assumption on conditional variance of the squared error is imposed. A simulation study is performed to provide evidence of how the tests work and compare with tests that have appeared in the literature. The approach may readily be extended to handle partial linear, and linear autoregressive models.
Similar content being viewed by others
References
Carroll, R. J., Ruppert, D., Transformation and Weighting in Regression, New York: Chapman and Hall, 1988.
Cook, R. D., Weisberg, S., Diagnostics for heteroscedasticity in regression, Biometrika, 1988, 70: 1–10.
Davidian, M., Carroll, R. J., Variance function estimation, J. Amer. Statist. Assoc., 1987, 82: 1079–1091.
Bickel, P., Using residuals robustly I: Tests for heteroscedasticity, Ann. Statist., 1978, 6: 266–291.
Carroll, R. J., Ruppert, D., On robust tests for heteroscedasticity, Ann. Statist., 1981. 9: 205–209.
Eubank, R. L., Thomas, W., Detecting heteroscedasticity in nonparametric regression, J. Roy. Statist. Soc., Ser. B, 1993, 55: 145–155.
Diblasi, A., Bowman, A., Testing for constant variance in a linear model, Statist. and Probab. Letters, 1997, 33: 95–103.
Dette, H., Munk, A., Testing heteoscedasticity in nonparametric regression, J. R. Statist. Soc. B, 1998, 60: 693–708.
Müller, H. G., Zhao, P. L., On a semi-parametric variance function model and a test for heteroscedasticity, Ann. Statist., 1995, 23: 946–967.
Stute, W., Manteiga, G., Quindimil, M. P., Bootstrap approximations in model checks for regression, J. Amer. Statist. Asso., 1998, 93: 141–149.
Stute, W., Thies, G., Zhu, L. X., Model checks for regression: An innovation approach, Ann. Statist., 1998, 26: 1916–1939.
Shorack, G. R., Wellner, J. A., Empirical Processes with Applications to Statistics, New York: Wiley, 1986.
Efron, B., Bootstrap methods: Another look at the jackknife, Ann. Statist., 1979, 7: 1–26.
Wu, C. F. J., Jackknife, bootstrap and other re-sampling methods in regression analysis, Ann. Statist., 1986, 14: 1261- 1295.
Härdle, W., Mammen, E., Comparing non-parametric versus parametric regression fits, Ann. Statist., 1993, 21: 1926- 1947.
Liu, R. Y., Bootstrap procedures under some non-i.i.d. models, Ann. Statist., 1988, 16: 1696–1708.
Pollard, D., Convergence of Stochastic Processes, New York: Springer-Verlag, 1984.
Ginb, E., Zinn, J., On the central limit theorem for empirical processes (with discussion), Ann. Probab., 1984, 12: 929–998.
Nolan, D., Pollard, D., U-process: Rates of convergence, Ann. Statist., 1987, 15: 780–799.
Zhu, L. X., Convergence rates of the empirical processes indexed by the class of functions with applications, J. System Sci. Math. Scis (in Chinese), 1993, 13: 33–41.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhu, L., Fujikoshi, Y. & Naito, K. Heteroscedasticity checks for regression models. Sci. China Ser. A-Math. 44, 1236–1252 (2001). https://doi.org/10.1007/BF02877011
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02877011