×

zbMATH — the first resource for mathematics

Smoothing-based lack-of-fit tests: Variations on a theme. (English) Zbl 0877.62041
Summary: In recent years a number of authors have studied lack-of-fit tests that make use of nonparametric smoothing ideas. Some of these tests, such as those proposed by R. L. Eubank and J. D. Hart [Ann. Stat. 20, No. 3, 1412-1425 (1992; Zbl 0776.62045)] utilize data-driven smoothing parameters as test statistics. In this paper variations and alternative forms of the Eubank-Hart test are explored. The tests considered are based upon trigonometric series regression estimators whose smoothing parameter is the point at which the series is truncated. It is shown that one variation based on an \(L_2\) discrepancy measure is exceptionally powerful in detecting high frequency departures from the hypothesized regression model.
The tests are shown to be applicable in both fixed- and random-design regression problems. A convenient graphical means of describing the results of one of our tests is illustrated by example, and a simulation study compares the proposed tests to some existing ones.

MSC:
62G10 Nonparametric hypothesis testing
62G07 Density estimation
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] DOI: 10.1093/biomet/76.1.1 · Zbl 0663.62096 · doi:10.1093/biomet/76.1.1
[2] Azzalini A., Journal of the Royal Statistical Society 55 pp 549– (1993)
[3] DOI: 10.1214/aos/1176347753 · Zbl 0706.62046 · doi:10.1214/aos/1176347753
[4] DOI: 10.1214/aos/1176342823 · Zbl 0307.62036 · doi:10.1214/aos/1176342823
[5] Bhattacharya R. N., Normal Approximation and Asymptotic Expansions · Zbl 1222.41002 · doi:10.1137/1.9780898719895
[6] Butzer P. L., Fourier Analysis and Approximation (1971) · Zbl 0217.42603 · doi:10.1007/978-3-0348-7448-9
[7] Carroll R. J., Transformation and Weighting in Regression (1988) · Zbl 0666.62062 · doi:10.1007/978-1-4899-2873-3
[8] DOI: 10.1016/0167-7152(94)90070-1 · Zbl 0793.62026 · doi:10.1016/0167-7152(94)90070-1
[9] DOI: 10.1016/0167-7152(93)90167-H · Zbl 0771.62034 · doi:10.1016/0167-7152(93)90167-H
[10] Diggle P., Time Series, A Biostatistical Introduction (1990) · Zbl 0727.62083
[11] DOI: 10.2307/2289774 · Zbl 0702.62037 · doi:10.2307/2289774
[12] DOI: 10.1214/aos/1176348775 · Zbl 0776.62045 · doi:10.1214/aos/1176348775
[13] DOI: 10.1093/biomet/80.1.89 · Zbl 0792.62042 · doi:10.1093/biomet/80.1.89
[14] Eubank R. L., Annals of Statistics (1996)
[15] DOI: 10.1093/biomet/78.2.245 · doi:10.1093/biomet/78.2.245
[16] DOI: 10.1093/biomet/73.3.625 · Zbl 0649.62035 · doi:10.1093/biomet/73.3.625
[17] Grenander U., Statistical Analysis of Stationary Time Series · Zbl 0080.12904 · doi:10.1063/1.3060405
[18] DOI: 10.1016/0047-259X(83)90024-6 · Zbl 0522.62029 · doi:10.1016/0047-259X(83)90024-6
[19] DOI: 10.2307/2289600 · Zbl 0717.62037 · doi:10.2307/2289600
[20] DOI: 10.1093/biomet/77.3.521 · Zbl 1377.62102 · doi:10.1093/biomet/77.3.521
[21] DOI: 10.1214/aos/1176349403 · Zbl 0795.62036 · doi:10.1214/aos/1176349403
[22] DOI: 10.2307/2290639 · Zbl 0764.62036 · doi:10.2307/2290639
[23] DOI: 10.1016/0167-7152(91)90085-6 · doi:10.1016/0167-7152(91)90085-6
[24] DOI: 10.1093/biomet/76.1.39 · Zbl 0664.62068 · doi:10.1093/biomet/76.1.39
[25] DOI: 10.1214/aoms/1177731677 · Zbl 0060.29911 · doi:10.1214/aoms/1177731677
[26] Priestley M. B., Spectral Analysis and Time Series (1981) · Zbl 0537.62075
[27] Ramachandran M. Testing Goodness of Fit Using Nonparametric Techniques Ph.D. dissertation Department of Statistics, Texas A and M University 1993
[28] DOI: 10.1002/9780470316436 · Zbl 0256.62002 · doi:10.1002/9780470316436
[29] DOI: 10.1002/9780470316481 · Zbl 0538.62002 · doi:10.1002/9780470316481
[30] DOI: 10.1090/S0002-9947-1956-0079851-X · doi:10.1090/S0002-9947-1956-0079851-X
[31] DOI: 10.2307/2290398 · Zbl 0736.62063 · doi:10.2307/2290398
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.