Analytical chemistry council

METHODS AND OBJECTS OF CHEMICAL ANALYSIS

ISSN title: "Metody i obʺekty himičeskogo analiza"

An international journal devoted to all aspects of Analytical chemistry

ISSN 2413-6166 (Online), ISSN 1991-0290 (Print)

Kiev University
  Ukr | En
Home  Call for papers ReceivedContact us
cover

Alternative Methods for Constructing of Linear Regressions

M.O. Onizhuk, V.V. Ivanov*, A.V. Panteleimonov, Yu.V. Kholin

* Corresponding author

V.N. Karazin Kharkiv National University, 4 Svobody Sq., Kharkiv, 61022, Ukraine;
*e-mail: vivanov@karazin.ua

Methods Objects Chem. Anal., 2017, 12(3), p. 105-111

https://doi.org/10.17721/moca.2017.105-111

Buy Article:

2 USD plus tax

DOI Id

preview the article

Abstract

Different approaches to solution of linear regression problem have been implemented and tested with Python programming language. The described methods are based on two concepts: the minimization of deviation of calculated value from experimental one of the dependent variable (methods OLS, Ordinary Least Squares, and LAD, Least Absolute Deviation) and the minimization of the errors perpendicular to the regression line (methods ODR, Orthogonal Distance Regression, and LADOD, Least Absolute Deviation of Orthogonal Distances). The significant influence of the chosen function on the regression equation has been demonstrated. The set of examples, including the model problems as well as the experimental datasets, shows the importance of appropriate selection of regression model when the spread in data is significant. In such a situation, the proposed in article new method LADOD “Least absolute deviations of Orthogonal Distances” demonstrated adequate description of the system.

Keywords: QSAR, regression, least square method, least absolute deviation, orthogonal distance regression

Article language: Rus

ReferencesPreview
 

Publisher:Taras Shevchenko National University, Kiev Ukraine

(Analytical chemistry department at Taras Shevchenko National University, 64 Vladimirskaya STR., Kiev, 01601 UKRAINE)
analysis@univ.kiev.ua, www.univ.kiev.ua, +380-44-2393266

The journal is indexed in SCOPUS and Web of Science

The journal website: www.moca.net.ua

The articles in this journal are licensed under CC BY 4.0