Stepwise regression is a commonly used tool if the order of the linear model to be tted is not known exactly. In this note strategies are proposed for an optimal choice of both the design and the decision rule which selects the adequate model.

In this paper, a new derivation of a uniformly-convergent, second-order method for singularly-perturbed, linear ordinary differential equations based on the freezing of the coefficients of the differential equation, and integration of the resulting equations subject to continuity and smoothness conditions at the nodes, is presented. The derivation presented here is compared with others based on...

Starting from discrete event simulations based on sampled data we simulate the interplay between product density and flux. Data-fitting helps to determine the right parameters for clearing functions to close first and second order conservation laws. For the first order case well-known relations from M/M/1-queuing theory can be reproduced and numerically extended to transient behavior. To includ...

The exponential fitting technique uses information on the expected behaviour of solution a differential problem to define accurate and efficient numerical methods. In particular, exponentially fitted methods are very effective when applied problems with oscillatory solutions. this cases, compared standard methods, they have proved be even using large integration steps. paper we consider Runge-K...

Mesh adaptation for immersed solid is one of the most challenging topics in computational mechanics. In this contribution, we propose a novel anisotropic adaptive body-fitted mesh method particular Computational Fluid Dynamics (CFD) where boundary layers and high gradient solution at fluid–solid interface play major role. It characterized by its simplicity to implement, generality tackle comple...