Computing Parameter Estimates of a Homogeneous Nested Piecewise Linear Regression

Abstract

Objective. The aim of the study is to develop an algorithm for identifying the parameters of a homogeneous nested piecewise linear regression model of the first type by the method of least modules. Method. Estimation of its unknown parameters is carried out with the help of reduction to the problem of linear Boolean programming. Its solution should not cause computational difficulties due to a significant number of effective software tools - for example, the well-established and freely available program LPsolve on the Internet. Result. The generated linear programming problem has an acceptable dimension for solving practical modeling problems. Conclusion. The results of solving a numerical example indicate the effectiveness of the method proposed in the work for calculating parameter estimates for a homogeneous nested piecewise linear regression model of the first type by the method of least modules.

Keywords

• homogeneous nested piecewise linear regression
• parameter identification
• least moduli method
• linear boolean programming problem
• dimension