Abstract
AbstractThe linear regression analysis problems are considered under the assumption of the presence of noise in the output and input variables. To estimate the measure of approximation of the initial data, the \(l_1\) metric is used, which has a probabilistic rationale as a maximum likelihood method for two-sided exponential noise distribution. This approximation problem can also be interpreted as an improper (has no solution) interpolation problem, for which it is required to change (correct) optimally the positions of the points so that they all lie on the same hyperplane. In addition, the case of preliminary linear data transformation is considered, while the original information matrix is subject to correction. Therefore, the arising problems belong to the new class of parametric correction. It is shown that these approximation (corrections) problems can be reduced to a set of a finite number of linear programming problems.KeywordsData processingRegression analysisParametric correctionMaximum likelihood methodTwo-sided exponential distribution
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.