Algorithms for regression and classification [Elektronische Ressource] : robust regression and genetic association studies / von Robin Nunkesser

Robin Nunkesser

Description

Algorithms for Regression and ClassificationRobust Regression and Genetic Association StudiesDissertationzur Erlangung des Grades einesDoktors der Naturwissenschaftender Technischen Universität Dortmundan der Fakultät für InformatikvonRobin NunkesserDortmund2009Tag der mündlichen Prüfung: 24.02.2009Dekan: Professor Dr. Peter BuchholzGutachter: Juniorprofessor Dr. Thomas JansenProfessor Dr. Roland FriediiiAbstractRegression and classification are statistical techniques that may be used to extractrules and patterns out of data sets. Analyzing the involved algorithms comprises in-terdisciplinary research that offers interesting problems for statisticians and computerscientists alike. The focus of this thesis is on robust regression and classification ingenetic association studies.In the context of robust regression, new exact algorithms and results for robustonline scale estimation with the estimatorsQ andS and for robust linear regressionn nin the plane with the estimator least quartile difference (LQD) are presented. Addi-tionally, an evolutionary computation algorithm for robust regression with differentestimators in higher dimensions is devised. These estimators include the widely usedleast median of squares (LMS) and least trimmed squares (LTS).For classification in genetic association studies, this thesis describes a Genetic Pro-gramming algorithm that outpeforms the standard approaches on the considered datasets.

Sujets

• Mathematics

Informations

• Publié par: technischen_universitat_dortmund
• Publié le: 01 janvier 2009
• Nombre de lectures: 35
• Langue: English
• Poids de l'ouvrage: 9 Mo

Extrait