We propose a variational mode decomposition approach to estimate the variance function in a nonparametric heteroscedastic fixed design regression model. A data-driven estimator is constructed by applying variational mode decomposition technique to the difference-based initial estimates. The numerical results show that the proposed estimator performs better than the existing variance estimation procedures in the mean square sense.
3 May 2020 in International Journal for Computational Methods in Engineering Science and Mechanics
In this article it is proposed to solve numerically the Blasius viscous flow problem of fluid mechanics using wavelet Galerkin method. The spline wavelet system is used for this purpose. It is assumed that the approximate solution lies in the space spanned by translates of the scaling function of the considered wavelet system. It is found that the numerical solution thus obtained is having high accuracy when compared to the benchmark solution given by Howarth.
23 May 2025 in Journal of Statistical Theory and Practice