dc.contributor.author Baryamureeba, Venansius dc.date.accessioned 2022-07-18T11:28:49Z dc.date.available 2022-07-18T11:28:49Z dc.date.issued 2001 dc.identifier.citation Baryamureeba, V. (2001). The impact of equal weighting of low-and high-confidence observations on robust linear regression computations. BIT Numerical Mathematics, 41(5), 847-855. en_US dc.identifier.uri https://link.springer.com/article/10.1023/A:1021912522498 dc.identifier.uri https://nru.uncst.go.ug/handle/123456789/4222 dc.description.abstract Equal weighting of low- and high-confidence observations occurs for Huber, Talwar, and en_US Barya weighting functions when Newton’s method is used to solve robust linear regression problems. This leads to easy updates and/or downdates of existing matrix factorizations or easy computation of coefficient matrices in linear systems from previous ones. Thus Newton’s method based on these functions has been shown to be computationally cheap. In this paper we show that a combination of Newton’s method and an iterative method is a promising approach for solving robust linear regression problems. We show that Newton’s method based on the Talwar function is an active set method. Further we show that it is possible to obtain improved estimates of the solution vector by combining a line search method like Newton’s method with an active set method. dc.language.iso en en_US dc.publisher BIT Numerical Mathematics en_US dc.subject Robust linear regression en_US dc.subject Newton’s method en_US dc.subject Conjugate gradient least squares method en_US dc.subject LSQR en_US dc.subject Preconditioner en_US dc.subject Basis identification techniques en_US dc.title The Impact of Equal Weighting of Low and High-Confidence Observations on Robust Linear Regression Computations en_US dc.type Other en_US
﻿