Print Email Facebook Twitter The choices of weights in the iterative convex minorant algorithm Title The choices of weights in the iterative convex minorant algorithm Author Smalbil, P.J. Contributor Jongbloed, G. (mentor) Faculty Electrical Engineering, Mathematics and Computer Science Department Mathematics Programme Statistics Date 2015-01-19 Abstract In statistics one often encounters the problem of estimating a function based on a given dataset. Sometimes shape properties such as monotonicity of the function are known. This property can be used in a non-parametric regression model. The iterative convex minorant(ICM) algorithm can be used to compute an estimate of a convex regression function. In the ICM algorithm positive weights can be chosen arbitrarily. In this thesis we describe the (solution of the) isotonic regression problem, explain the ICM algorithm, describe the convex regression problem and present a simulation study to assess the effect of the choice of weights. Subject statisticsconvex regressionnon-parametric regressioniterative convex minorant algorithm To reference this document use: http://resolver.tudelft.nl/uuid:5a111157-1a92-4176-9c8e-0b848feb7c30 Part of collection Student theses Document type bachelor thesis Rights (c) 2015 Smalbil, P.J. Files PDF BSc_thesis_Smalbil_The-it ... orithm.pdf 672.67 KB Close viewer /islandora/object/uuid:5a111157-1a92-4176-9c8e-0b848feb7c30/datastream/OBJ/view