Linear regression modeling in monitoring tasks based on the method of least absolute deviations

Abstract

Algorithm for the exact solution of the problem of estimating the parameters of linear regression models by the least absolute deviations method is described. It is based on the descent through the nodal straight lines. This algorithm significantly outperforms other well-known methods of solving the problem and it can be effectively used in practice. The computational complexity of the descent algorithm through the nodal straight lines is assessed. © 2021 Author(s).