Title:

Segmented Regression Based on the Principle of Cut-off Polynomials with a Solved Economic Example

Group publication title:

20-th AMSE. Applications of Mathematics and Statistics in Economics. International Scientific Conference: Szklarska Poręba, 30 August- 3 September 2017. Conference Proceedings Full Text Papers

Creator:

Kaňka, Miloš

Subject and Keywords:

Cut-off polynomials ; system of normal equations ; indexes of determination ofobserved values

Description:

20-th AMSE. Applications of Mathematics and Statistics in Economics. International Scientific Conference: Szklarska Poręba, 30 August- 3 September 2017. Conference Proceedings Full Text Papers, s. 235-246

Abstrakt:

This article deals with segmented regression that is based on the so called cut-off polynomials of the first, or second, respectively third order. Most of the attention is given to the inference of the system of the normal equations gained by minimisation of the criterion of the least squares method. Certain attention is also given to the calculation of the unknowns of such a system with one of the Gauss methods. Parametric equations of the output regressive curve in the given model and the determination indexes of the observed variables are inferred. Those indexes also enable to assess the "quality" of each model. The author of this article also wrote a program for the three types of segmented regression. This program helps solve the aforementioned phases in much faster and simpler way

Publisher:

Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu

Place of publication:

Wrocław

Date:

2017

Resource Type:

materiały konferencyjne

Format:

application/pdf

Resource Identifier:

doi:10.15611/amse.2017.20.19

Language:

eng

Relation:

20-th AMSE. Applications of Mathematics and Statistics in Economics. International Scientific Conference: Szklarska Poręba, 30 August- 3 September 2017. Conference Proceedings Full Text Papers

Rights:

Wszystkie prawa zastrzeżone (Copyright)

Access Rights:

Dla wszystkich w zakresie dozwolonego użytku

Location:

Uniwersytet Ekonomiczny we Wrocławiu