zbMATH — the first resource for mathematics

A simple variable selection technique for nonlinear models. (English) Zbl 1008.62620
Summary: Applying nonparametric variable selection criteria in nonlinear regression models generally requires a substantial computational effort if the data set is large. In this paper we present a selection technique that is computationally much less demanding and performs well in comparison with methods currently available. It is based on a polynomial approximation of the nonlinear model. Performing the selection only requires repeated least squares estimation of models that are linear in parameters. The main limitation of the method is that the number of variables among which to select cannot be very large if the sample is small and the order of an adequate polynomial at the same time is high. Large samples can be handled without problems.

62J02 General nonlinear regression
62G99 Nonparametric inference
Full Text: DOI
[1] Akaike H., Annals of the Institute of Statistical Mathematics 21 pp 243– (1974) · Zbl 0202.17301
[2] DOI: 10.1109/TAC.1974.1100705 · Zbl 0314.62039
[3] DOI: 10.1016/0005-1098(78)90005-5 · Zbl 0418.93079
[5] DOI: 10.1080/02331889508802499 · Zbl 0836.62067
[6] Yao Q., Statistica Sinica 4 pp 51– (1994)
[7] DOI: 10.1093/biomet/77.4.669
[8] DOI: 10.2307/2291003 · Zbl 0813.62037
[9] DOI: 10.1111/1467-9892.00193 · Zbl 0974.62077
[10] Royden H., Real Analysis (1963) · Zbl 0121.05501
[11] White H., Asymptotic Theory for Econometricians (1984)
[12] Priestley M., Spectral Analysis and Time Series (1981) · Zbl 0537.62075
[13] Judge G. G., The Theory and Practice of Econometrics (1985)
[14] Teräsvirta T., Scandinavian Journal of Statistics 13 pp 159– (1986)
[15] DOI: 10.1111/j.1467-9892.1993.tb00139.x · Zbl 04512015
[16] DOI: 10.1111/1467-9868.00203 · Zbl 0952.62039
[17] DOI: 10.2307/2291217
[18] Silverman B., Density Estimation for Statistics and Data Analysis (1986) · Zbl 0617.62042
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.