Trapezoidal rule and sampling designs for the nonparametric estimation of the regression function in models with correlated errors

Djihad Benelmadani (1) , Karim Benhenni (1) , Sana Louhichi (1)

1 IPS - Inférence Processus Stochastiques

The problem of estimating the regression function in a fixed design models with correlated observations is considered. Such observations are obtained from several experimental units, each of them forms a time series. Based on the trapezoidal rule, we propose a simple kernel estimator and we derive the asymptotic expression of its integrated mean squared error IMSE and its asymptotic normality. The problems of the optimal bandwidth and the optimal design with respect to the asymptotic IMSE are also investigated. Finally, a simulation study is conducted to study the performance of the new estimator and to compare it with the classical estimator of Gasser and Müller in a finite sample set. In addition, we study the robustness of the optimal design with respect to the misspecification of the autocovariance function.

Mots clés: Nonparametric regression; autocovariance function; optimal design; trapezoidal rule; asymptotic normality

Domaines: Statistiques [math.ST]

Djihad Benelmadani, Karim Benhenni, Sana Louhichi. Trapezoidal rule and sampling designs for the nonparametric estimation of the regression function in models with correlated errors. Statistics, 2020, 54 (1), pp.59-96. ⟨10.1080/02331888.2020.1715409⟩. ⟨hal-01892123⟩