×

zbMATH — the first resource for mathematics

Order choice in nonlinear autoregressive models. (English) Zbl 0836.62067
Summary: An extensive literature has been devoted to the problem of order choice in autoregressive models. Most of alternative methods to hypothesis tests are based on the minimization of the Akaike Information Criterion (AIC) or on some of its variants. These methods have the main drawback to have to assume a parametric form for the autoregression function.
The aim of this paper is to present a nonparametric approach that allows to estimate the autoregression order without limiting ourself to any restrictive parametric class of processes. Our technique is in the same spirit as AIC criterion, in the sense that it is based on the minimization of some prediction error. Both theoretical and computational aspects of this method are discussed in this paper.

MSC:
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62G05 Nonparametric estimation
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] DOI: 10.1093/biomet/77.4.669
[2] DOI: 10.1007/BF02532251 · Zbl 0202.17301
[3] DOI: 10.1007/BF02506337 · Zbl 0259.62076
[4] DOI: 10.1093/biomet/66.2.237 · Zbl 0407.62064
[5] DOI: 10.2307/2290456 · Zbl 0763.62019
[6] DOI: 10.1111/j.1467-9892.1992.tb00102.x · Zbl 0754.62018
[7] Cheng B., J. Roy. Statist. Soc. 54 pp 427– (1992)
[8] DOI: 10.2307/1403039 · Zbl 0471.62039
[9] DOI: 10.1007/BF00533708 · Zbl 0525.62046
[10] Daukhan P., Lecture Notes in Statistics 85 (1994)
[11] Delecroix, M. 1987. ”Sur l’estimation non paramétrique des processus ergodiques”. France Thesis at Univ. Lille-Flandres-Artois
[12] Ferre L., Public. Lab. Statist. et Probabilités (1990)
[13] DOI: 10.2307/2290393 · Zbl 0733.62047
[14] Györfi L., Nonparametric curve estimation from Time Series 60 (1989) · Zbl 0697.62038
[15] DOI: 10.1214/aos/1176345144 · Zbl 0451.62068
[16] DOI: 10.1016/0047-259X(81)90089-0 · Zbl 0501.93065
[17] DOI: 10.1111/j.1467-9892.1986.tb00484.x · Zbl 0588.62163
[18] Hannan E., J. Roy, Statist. Soc. 1 pp 190– (1979)
[19] Härdle W., Applied Nonparametric Regression (1990) · Zbl 0714.62030
[20] DOI: 10.1080/02331888708801986 · Zbl 0622.62043
[21] Härdle W., Nonparametric Functional Estimation pp 111– (1990)
[22] DOI: 10.1214/aos/1176349748 · Zbl 0594.62043
[23] DOI: 10.1111/j.1467-9892.1992.tb00103.x · Zbl 0759.62016
[24] DOI: 10.1214/aos/1176347630 · Zbl 0703.62045
[25] DOI: 10.2307/2285938 · Zbl 0309.62064
[26] DOI: 10.2307/1267787 · Zbl 0485.62086
[27] DOI: 10.2307/2346970
[28] DOI: 10.1109/TAC.1974.1100733 · Zbl 0317.62063
[29] DOI: 10.1214/aos/1176346253 · Zbl 0521.62072
[30] DOI: 10.1111/j.1467-9892.1990.tb00049.x · Zbl 0703.62099
[31] DOI: 10.1111/j.1467-9892.1983.tb00368.x · Zbl 0544.62082
[32] DOI: 10.1016/0005-1098(78)90005-5 · Zbl 0418.93079
[33] Rosenblatt, M. A central limit theorem and a strong mixing condition. Proc. Nat. Acad. Sci. USA. Vol. 42, pp.43–47. · Zbl 0070.13804
[34] Roussas, G. ”Nonparametric regression estimation under mixing conditions”. Preprint · Zbl 0699.62038
[35] Roussas G., Statistical Theory and Data Analysis II pp 293– (1988)
[36] DOI: 10.1214/aos/1176344136 · Zbl 0379.62005
[37] DOI: 10.1093/biomet/63.1.117 · Zbl 0358.62048
[38] DOI: 10.1214/aos/1176344897 · Zbl 0425.62069
[39] Silverman B. W., J. Roy. Statist. Soc. 47 pp 1– (1985)
[40] DOI: 10.1214/aos/1176345969 · Zbl 0511.62048
[41] Stone M., J. Roy. Statist. Soc 2 pp 276– (1979)
[42] DOI: 10.2307/3212863 · Zbl 0314.62038
[43] DOI: 10.1016/0167-7152(90)90073-G · Zbl 0778.62036
[44] DOI: 10.1214/aos/1176348513 · Zbl 0764.62038
[45] Vieu P., Nonparametric Functional Estimation pp 271– (1991)
[46] DOI: 10.1016/0047-259X(91)90105-B · Zbl 0751.62022
[47] Vieu P., Computer Intensive Methods in Statistics 1 (1993)
[48] DOI: 10.1016/0167-9473(94)90149-X · Zbl 0937.62583
[49] DOI: 10.1016/0047-259X(89)90091-2 · Zbl 0701.62049
[50] DOI: 10.1214/aos/1176348375 · Zbl 0738.62051
[51] DOI: 10.2307/2290211 · Zbl 0781.62106
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.