Abstract
We propose an algorithm for computing parameter estimates for a smoothing cubic spline that minimize the estimated expectation of losses. Instead of the usual assumption that the noise is centered we use an assumption which is more realistic for many practical smoothing problems, namely that it is zero median. The problem setting is augmented by prior deterministic information in the form of constraints on linear combinations of parameters of spline functions. We obtain explicit representations of such estimates and give their qualitative interpretation. Based on the results of a numerical experiment, we establish a high degree of robustness of the solutions to the presence of outliers in the measurements, including same sign outliers, and the possibility to fairly reliably determine the actual accuracy of the resulting estimates of spline parameters by the attained minimum risk value.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Huber, P.J., Robust Statistics, New York: Wiley, 1981. Translated under the title Robastnost’ v statistike, Moscow: Mir, 1984.
Terikhova, N.I, Cubic Smoothing Splines, Mat. Modelir., 1990, vol. 2, no. 8, pp. 112–118.
Granichin, O.N. and Polyak, B.T., Randomizirovannye algoritmy otsenivaniya i optimizatsii pri pochti proizvol’nykh pomekhakh (Randomized Estimation and Optimization Algorithms for Almost Arbitrary Noise), Moscow: Nauka, 2003.
Weyer Erik, Ko Sangho, and Campi, M.C, Proc. 48th Conf. on Decision and Control, Shanghai, China, 2009, pp. 92–98.
Balk, P.I, Estimation of Functional Dependency Parameters at Zero Median Value of Noises in Measurements, Autom. Remote Control, 2011, vol. 72, no. 5, pp. 964–974.
Vapnik, V.N., Vosstanovlenie zavisimostei po empiricheskim dannym (Reconstructing Dependencies by Empirical Data), Moscow: Nauka, 1979.
Orlik, P. and Terao, H., Arrangements of Hyperplanes, Berlin–Heidelberg; Springer-Verlag, 1992.
Shpakov, P.S. and Popov, V.N., Statisticheskaya obrabotka eksperimental’nykh dannykh (Statistical Processing of Experimental Data), Moscow: MGTU, 2003.
Ahlberg, J.H., Nilson, E.N., andWalsh, J.L., The Theory of Splines and Their Applications, Mathematics in Science and Engineering, vol. 38, New York–London: Academic, 1967. Translated under the title Teoriya splainov i ee prilozheniya, Moscow: Mir, 1972.
Stechkin, S.B. and Subbotin, Yu.N., Splainy v vychislitel’noi matematike (Splines in Computational Mathematics), Moscow: Nauka, 1976.
Zav’yalov, Yu.S., Kvasov, B.I., and Miroshnichenko, V.L., Metody splain-funktsii (Methods of Spline Functions), Moscow: Nauka, 1980.
de Boor, C., A Practical Guide to Splines, New York: Springer, 1978. Translated under the title Prakticheskoe rukovodstvo po splainam, Moscow: Radio i Svyaz’, 1985.
Voskoboinikov, Yu.E, Frequentist Approach to Estimating the Accuracy of Smoothing and Differentiation of Experimental Data with Smoothing Splines, Avtometriya, 1986, no. 1, pp. 38–47.
Malozemov, V.N. and Pevnyi, A.B., Polinomial’nye splainy (Polynomial Splines), Leningrad: ATU, 1986.
Volkov, V.G. and Nikulin, M.S., Nesmeshchennye otsenki i ikh primenenie (Unbiased Estimates and Their Application), Moscow: Nauka, 1989.
Kirushev, V.A. and Malozemov, V.N, Interpolation of Positive Data with Nonnegative Natural Cubic Splines, Vestn. S.-Peterb. Univ., Ser. 1, 1995, no. 2, pp. 25–30.
Voskoboinikov, Yu.E, Constructing Smoothing Cubic Splines in Automated Processing of Experimental Results, Avtometriya, 1979, no. 4, pp. 110–117.
Mikhal’skii, A.I, The Method of Averaged Splines in the Problem of Approximating Dependences on the Basis of Empirical Data, Autom. Remote Control, 1974, vol. 35, no. 3, part 1, pp. 382–386.
Tikhonov, A.N. and Arsenin, V.Ya., Metody reshenii nekorrektnykh zadach (Methods for Solving Ill- Posed Problems), Moscow: Nauka, 1979.
Chernous’ko, F.L, Optimal Guaranteed Estimates of Uncertainties with Ellipsoids. I, Izv. Akad. Nauk SSSR, Tekhn. Kibern., 1980, no. 3, pp. 3–11.
Kurzhanskii, A.B, The Identification Problem—Theory of Guaranteed Estimates, Autom. Remote Control, 1991, vol. 52, no. 4, part 1, pp. 447–465.
Anskombe, F.J, Graphs in Statistical Analysis, Am. Statistician, 1973, no. 27, pp. 17–21.
Raifa, G., Analiz reshenii (Analysis of Solutions), Moscow: Nauka, 1977.
Vapnik, V.N. and Chervonenkis, A.Ya., Teoriya raspoznavaniya obrazov (Image Recognition Theory), Moscow: Nauka, 1974.
Mudrov, V.I. and Kushko, V.L., Metod naimen’shikh modulei (Method of Least Absolute Values), Moscow: Znanie,1971.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © P.I. Balk, A.S. Dolgal’, 2017, published in Avtomatika i Telemekhanika, 2017, No. 6, pp. 138–156.
This paper was recommended for publication by O.N. Granichin, a member of the Editorial Board
Rights and permissions
About this article
Cite this article
Balk, P.I., Dolgal’, A.S. Spline smoothing for experimental data under zero median of the noise. Autom Remote Control 78, 1072–1086 (2017). https://doi.org/10.1134/S000511791706008X
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S000511791706008X