×

Using local linear kernel smoothers to test the lack of fit of nonlinear regression models. (English) Zbl 1248.62056

Summary: We propose a data-driven test that assesses the lack of fit of nonlinear regression models. The comparison of local linear kernel and parametric fits is the basis of this test, and specific boundary-corrected kernels are not needed at the boundary when local linear fitting is used. Under the parametric null model, the asymptotically optimal bandwidth can be used for bandwidth selection. This selection method leads to a data-driven test that has a limiting normal distribution under the null hypothesis and is consistent against any fixed alternative. The finite-sample property of the proposed data-driven test is illustrated, and the power of the test is compared with that of some existing tests via simulation studies. We illustrate the practicality of the proposed test by using two data sets.

MSC:

62G08 Nonparametric regression and quantile regression
62G10 Nonparametric hypothesis testing
62J02 General nonlinear regression
62G20 Asymptotic properties of nonparametric inference
65C60 Computational problems in statistics (MSC2010)
Full Text: DOI

References:

[1] Alcalá, J. T.; Cristóbal, J. A.; González-Manteiga, W., Goodness-of-fit test for linear models based on local polynomials, Statist. Probab. Lett., 42, 39-46 (1999) · Zbl 0946.62016
[2] Allen, D. L., Hypothesis testing using an L-1-distance bootstrap, Amer. Statist., 51, 145-150 (1997)
[3] Anderson, N. H.; Hall, P.; Titterington, D. M., 2-sample test statistics for measuring discrepancies between two multivariate probability density functions using kernel-based density estimates, J. Multivariate Anal., 50, 41-54 (1994) · Zbl 0798.62055
[4] Anderson, N. H.; Titterington, D. M., Some methods for investigating spatial clustering, with epidemiological applications, J. Roy. Statist. Soc. Ser. A, 160, 87-105 (1997)
[5] Barry, D.; Hartigan, J. A., An omnibus for departures from constant mean, Ann. Statist., 18, 1340-1357 (1990) · Zbl 0706.62046
[6] Cox, D.; Koh, E.; Wahba, G.; Yandell, B., Testing the (parametric) null model hypothesis in (semiparametric) partial and generalized spline models, Ann. Statist., 16, 113-119 (1988) · Zbl 0673.62017
[7] Eppright, E. S.; Fox, H. M.; Fryer, B. A.; Lamkin, G. H.; Vivian, V. M.; Fuller, E. S., Nutrition of infants and preschool children in the north central region of the United states of America, World Rev. Nutr. Diet., 14, 269-332 (1972)
[8] Eubank, R. L., Spline Smoothing and Nonparametric Regression (1988), Marcel Dekker: Marcel Dekker New York · Zbl 0702.62036
[9] Eubank, R. L.; Spiegelman, C. H., Testing the goodness of fit of a linear model via nonparametric regression techniques, J. Amer. Statist. Assoc., 85, 387-392 (1990) · Zbl 0702.62037
[10] Eubank, R. L.; Li, C. S.; Wang, S., Testing lack-of-fit of parametric regression models using nonparametric regression techniques, Statist. Sinica, 15, 135-152 (2005) · Zbl 1059.62042
[11] Fan, J.; Gijbels, I., Local Polynomial modelling and Its Applications (1996), Chapman & Hall: Chapman & Hall London. · Zbl 0873.62037
[12] Fan, Y. Q., Goodness-of-fit tests based on kernel density estimators with fixed smoothing parameter, Econom. Theory, 14, 604-621 (1998)
[13] Fan, Y. Q.; Ullah, A., On goodness-of-fit tests for weekly dependent processes using kernel method, J. Nonparametr. Statist., 11, 337-360 (1999) · Zbl 0955.62044
[14] Gasser, T.; Sroka, L.; Jennen-Steinmetz, C., Residual variance and residual pattern in nonlinear regression, Biometrika, 73, 625-633 (1986) · Zbl 0649.62035
[15] Gupta, A. K.; Henze, N.; Klar, B., Testing for affine equivalence of elliptically symmetric distributions, J. Multivariate Anal., 88, 222-242 (2004) · Zbl 1035.62055
[16] Härdle, W.; Hall, P.; Marron, J. S., How far are automatically chosen regression smoothing parameters from their optimum? (with discussion), J. Amer. Statist. Assoc., 83, 86-99 (1988) · Zbl 0644.62048
[17] Härdle, W.; Mammen, M., Comparing nonparametric versus parametric regression fits, Ann. Statist., 21, 1926-1947 (1993) · Zbl 0795.62036
[18] Henze, N.; Penrose, M. D., On the multivariate runs test, Ann. Statist., 27, 290-298 (1999) · Zbl 0944.62057
[19] Heyde, C. C.; Brown, B. M., On the departure from normality of a certain class of martingales, Ann. Math. Statist., 14, 2161-2165 (1970) · Zbl 0225.60026
[20] Hjellvik, V.; Tjøstheim, D., Nonparametric tests of linearity for time series, Biometrika, 82, 351-368 (1995) · Zbl 0823.62044
[21] Hjellvik, V.; Tjøstheim, D., Nonparametric statistics for testing of linearity and serial independence, J. Nonparametr. Statist., 6, 223-251 (1996) · Zbl 0880.62049
[22] Horowitz, J. L.; Spokoiny, V. G., An adaptive, rate-optimal test of a parametric men-regression model against a nonparametric alternative, Econometrica, 69, 599-631 (2001) · Zbl 1017.62012
[23] Jenss, R. M.; Bayley, N., A mathematical method for studying the growth of a child, Hum. Biol., 9, 556-563 (1937)
[24] Kuchibhabhatla, M.; Hart, J. D., Smoothing-based lack-of-fit tests: variations on theme, J. Nonparametr. Statist., 7, 1-22 (1996) · Zbl 0877.62041
[25] Li, Q., Nonparametric testing the similarity of two unknown density functions: Local power and bootstrap analysis, J. Nonparametr. Statist., 11, 189-213 (1999) · Zbl 0955.62046
[26] Müller, H. G., Smooth optimum kernel estimators near endpoints, Biometrika, 78, 521-530 (1991) · Zbl 1192.62108
[27] Müller, H. G., Goodness-of-fit diagnostics for regression models, Scand. J. Statist., 19, 157-172 (1992) · Zbl 0760.62037
[28] Seber, G. A.F.; Wild, C. J., Nonlinear Regression (1988), Wiley: Wiley New York · Zbl 0721.62062
[29] Whittle, P., Bounds for the moments of linear and quadratic forms in dependent variables, Theory Probab. Appl., 5, 302-305 (1960)
[30] Wu, C. F.J., Jackknife, bootstrap and other resampling methods in regression analysis (with discussion), Ann. Statist., 14, 1261-1350 (1986) · Zbl 0618.62072
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.