zbMATH — the first resource for mathematics

Tests for the choice of approximative models in nonlinear regression when the variance is unknown. (English) Zbl 0808.62059
Summary: Nonlinear regression models are used in many fields. Often the regression for observation-covariate pairs \((X(t_ i), t_ i)\) is modeled as \(X(t_ i)= f(t_ i)+ \varepsilon (t_ i)\), \(i=1,\dots, n\), where \(f\) is the continuous possible nonlinear mean function, while the \((\varepsilon (t_ i) )_{i=1,\dots, n}\) are zero mean, i.i.d. random errors having finite variance \(\sigma^ 2\). The least squares methods for estimation of \(f\) are usually based upon a given parametric form of \(f\).
We develop two statistical tests, one for testing that \(f\) belongs to a given class of functions possibly discontinuous in their first derivative, and another one for comparing two such classes. This is done by introducing an appropriate estimate of the unknown variance \(\sigma^ 2\). The numerical results of a simulation study seem satisfactory.

62J02 General nonlinear regression
62F12 Asymptotic properties of parametric estimators
62F03 Parametric hypothesis testing
Full Text: DOI
[1] Abi Samra, L. 1989. ”Estimation et tests de rupture en regression. Projet D.E.A”. Université J, Fourier Grenoble.
[2] Benzekri, S. 1989. ”Etude des propriétés asymptotiques des estimateurs des moindres carrés pour des problèmes de régression à phases multiples”. Thèse Université J. Fourier Grenoble.
[3] DOI: 10.1080/02331889108802316 · Zbl 0738.62024 · doi:10.1080/02331889108802316
[4] Bunke H., Math. Operationsforsch. Statist., ser. Statistics 12 pp 7– (1981)
[5] Hall, Martingale limit theory and its applications (1980) · Zbl 0462.60045
[6] DOI: 10.1214/aoms/1177697731 · Zbl 0193.47201 · doi:10.1214/aoms/1177697731
[7] DOI: 10.2307/2287408 · Zbl 0437.62064 · doi:10.2307/2287408
[8] DOI: 10.1093/biomet/73.3.625 · Zbl 0649.62035 · doi:10.1093/biomet/73.3.625
[9] DOI: 10.1214/aos/1176346788 · Zbl 0554.62035 · doi:10.1214/aos/1176346788
[10] Saïdi, Y. 1986. ”Méthodes appliquées de détection et d’estimation de rupture dans des modèles de régression”. Thèse U.S.M.G. Grenoble.
[11] Zwanzig S., Math. Operationsforsch. Statist., set. Statistics 11 pp 23– (1980)
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.