×

Trigonometric series regression estimators with an application to partially linear models. (English) Zbl 0709.62041

Summary: Let \(\mu\) be a function defined on an interval [a,b] of finite length. Suppose that \(y_ 1,...,y_ n\) are uncorrelated observations satisfying \(E(y_ j)=\mu (t_ j)\) and \(var(y_ j)=\sigma^ 2\), \(j=1,...,n\), where the \(t_ j's\) are fixed design points. Asymptotic (as \(n\to \infty)\) approximations of the integrated mean squared error and the partial integrated mean squared error of trigonometric series type estimators of \(\mu\) are obtained. Our integrated squared bias approximations closely parallel those of J. Hall [ibid. 13, 234-256 (1983; Zbl 0522.62029)] in the setting of density estimation.
Estimators that utilize only cosines are shown to be competitive with the so-called cut-and-normalized kernel estimators. Our results for the cosine series estimator are applied to the problem of estimating the linear part of a partially linear model. An efficient estimator of the regression coefficient in this model is derived without undersmoothing the estimate of the nonparametric component. This differs from the result of J. Rice [Stat. Probab. Lett. 4, 203-208 (1986; Zbl 0628.62077)] whose nonparametric estimator was a partial spline.

MSC:

62G07 Density estimation
62G20 Asymptotic properties of nonparametric inference
62J99 Linear inference, regression
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Billingsley, P., (Probability and Measure (1986), Wiley: Wiley New York)
[2] Butzer, P.; Nessel, R., (Fourier Analysis and Approximation (1971), Academic Press: Academic Press New York) · Zbl 0217.42603
[3] Eubank, R. L.; Hart, J. D.; Speckman, P., (Trigonometric Series Estimators with an Application to Partially Linear Models (1987), Dept. of Statist., Southern Methodist University), Tech. Rep. No. SMU/DS/TR/210
[4] Gasser, Th; Müller, H. G., Kernel estimation of regression functions, (Gasser, Th; Rosenblatt, M., Smoothing Techniques for Curve Estimation (1979), Springer-Verlag: Springer-Verlag Heidelberg), 23-68
[5] Greblicki, W.; Pawlak, M., Fourier and Hermite series estimates of regression functions, Ann. Inst. Statist. Math. A, 37, 443-454 (1985) · Zbl 0623.62029
[6] Hall, P., On trigonometric series estimates of densities, Ann. Statist., 9, 683-685 (1981) · Zbl 0484.62057
[7] Hall, P., Measuring the efficiency of trigonometric series estimates of a density, J. Multivariate Anal., 13, 234-256 (1983) · Zbl 0522.62029
[8] Kronmal, R.; Tarter, M., The estimation of probability densities and cumulatives by Fourier series methods, J. Amer. Statist. Assoc., 63, 925-952 (1968) · Zbl 0169.21403
[9] Nadaraya, E. A., On estimating regression, Theoret. Probab. Appl., 9, 141-142 (1964) · Zbl 0136.40902
[10] Rafajlowicz, E., Nonparametric orthogonal series estimators of regression: A class attaining the optimal convergence rate in \(L_2\), Statist. Probab. Lett., 5, 219-224 (1987) · Zbl 0605.62030
[11] Rice, J., Convergence rates for partially splined models, Statist. Probab. Lett., 4, 203-208 (1986) · Zbl 0628.62077
[12] Rutkowski, L., On system identification by nonparametric function fitting, IEEE Trans. Automatic Control AC-27, 225-227 (1982) · Zbl 0471.93065
[13] Speckman, P., Kernel smoothing in partial linear models, J. Roy. Statist. Soc. Ser. B, 50, 413-456 (1988) · Zbl 0671.62045
[14] Stewart, G., (Introduction to Matrix Computations (1973), Academic Press: Academic Press New York) · Zbl 0302.65021
[15] Watson, G. S., Smooth regression analysis, Sankhyà Ser. A, 26, 359-372 (1964) · Zbl 0137.13002
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.