TY - JOUR

T1 - Using parameter elimination to solve discrete linear Chebyshev approximation problems

AU - Krivulin, Nikolai

N1 - Funding Information: Funding: This work was supported in part by the Russian Foundation for Basic Research grant number 20-010-00145.

PY - 2020/12/13

Y1 - 2020/12/13

N2 - We consider discrete linear Chebyshev approximation problems in which the unknown parameters of linear function are fitted by minimizing the least maximum absolute deviation of errors. Such problems find application in the solution of overdetermined systems of linear equations that appear in many practical contexts. The least maximum absolute deviation estimator is used in regression analysis in statistics when the distribution of errors has bounded support. To derive a direct solution of the problem, we propose an algebraic approach based on a parameter elimination technique. As a key component of the approach, an elimination lemma is proved to handle the problem by reducing it to a problem with one parameter eliminated, together with a box constraint imposed on this parameter. We demonstrate the application of the lemma to the direct solution of linear regression problems with one and two parameters. We develop a procedure to solve multidimensional approximation (multiple linear regression) problems in a finite number of steps. The procedure follows a method that comprises two phases: backward elimination and forward substitution of parameters. We describe the main components of the procedure and estimate its computational complexity. We implement symbolic computations in MATLAB to obtain exact solutions for two numerical examples.

AB - We consider discrete linear Chebyshev approximation problems in which the unknown parameters of linear function are fitted by minimizing the least maximum absolute deviation of errors. Such problems find application in the solution of overdetermined systems of linear equations that appear in many practical contexts. The least maximum absolute deviation estimator is used in regression analysis in statistics when the distribution of errors has bounded support. To derive a direct solution of the problem, we propose an algebraic approach based on a parameter elimination technique. As a key component of the approach, an elimination lemma is proved to handle the problem by reducing it to a problem with one parameter eliminated, together with a box constraint imposed on this parameter. We demonstrate the application of the lemma to the direct solution of linear regression problems with one and two parameters. We develop a procedure to solve multidimensional approximation (multiple linear regression) problems in a finite number of steps. The procedure follows a method that comprises two phases: backward elimination and forward substitution of parameters. We describe the main components of the procedure and estimate its computational complexity. We implement symbolic computations in MATLAB to obtain exact solutions for two numerical examples.

KW - discrete linear Chebyshev approximation

KW - minimax problem

KW - variable elimination

KW - direct solution

KW - multiple linear regression; least maximum absolute deviation estimator

KW - Direct solution

KW - Variable elimination

KW - Minimax problem

KW - Multiple linear regression

KW - Least maximum absolute deviation estimator

KW - Discrete linear Chebyshev approximation

KW - Key-Words: discrete linear Chebyshev approximation

KW - Minimiax problem

UR - http://www.scopus.com/inward/record.url?scp=85097947709&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/801da033-37a2-3155-ad64-a35fd375abd3/

U2 - 10.3390/math8122210

DO - 10.3390/math8122210

M3 - Article

VL - 8

SP - 1

EP - 16

JO - Mathematics

JF - Mathematics

SN - 2227-7390

IS - 12

M1 - 2210

ER -