Search Results - subject:"I-splines"

Bergersen, Linn Cecilie; Tharmaratnam, Kukatharmini; … - In: Computational Statistics & Data Analysis 77 (2014) C, pp. 336-351

-lasso) is constructed to select variables and estimate effects using monotone splines (I-splines). The additive components in …

Persistent link: https://www.econbiz.de/10010871489

SVM-Maj: a majorization approach to linear support vector machines with different hinge errors

Groenen, P.J.F.; Nalbantov, G.I.; Bioch, J.C. - Erasmus University Rotterdam, Econometric Institute - 2007

majorization, I-Splines, Absolute hinge error, Quadratic hinge error, Huber hinge error, Optimal scaling. 1 Introduction In recent … the transformation of the predictor variables. Instead of using kernels, we propose to use I-splines to accommodate …

Persistent link: https://www.econbiz.de/10005450870

SVM-Maj: a majorization approach to linear support vector machines with different hinge errors

Groenen, Patrick; Nalbantov, Nalbantov, G.I.; Bioch, … - Faculteit der Economische Wetenschappen, Erasmus … - 2007

Support vector machines (SVM) are becoming increasingly popular for the prediction of a binary dependent variable. SVMs perform very well with respect to competing techniques. Often, the solution of an SVM is obtained by switching to the dual. In this paper, we stick to the primal support vector...

Persistent link: https://www.econbiz.de/10010837908

Nonlinear support vector machines through iterative majorization and I-splines

Groenen, P.J.F.; Bioch, J.C.; Nalbantov, G.I. - Erasmus University Rotterdam, Econometric Institute - 2006

Nonlinear Support Vector Machines through Iterative Majorization and I-Splines P.J.F. Groenen⁄ G. Nalbantovy J.C. Bioch …: Support vector machines, Iterative majorization, I-Splines. 1 Introduction In recent years, support vector machines (SVMs … the reconstructed boundary in the right panel of Figure 6. I-Splines have the property that for nonnegative w the …

Persistent link: https://www.econbiz.de/10005450850

Nonlinear support vector machines through iterative majorization and I-splines

Groenen, Patrick; Bioch, Bioch, J.C.; Nalbantov, … - Faculteit der Economische Wetenschappen, Erasmus … - 2006

To minimize the primal support vector machine (SVM) problem, we propose to use iterative majorization. To do so, we propose to use it- erative majorization. To allow for nonlinearity of the predictors, we use (non)monotone spline transformations. An advantage over the usual ker- nel approach in...

Persistent link: https://www.econbiz.de/10010731825

Maximum marginal likelihood estimation for semiparametric item analysis

Ramsay, J.; Winsberg, S. - In: Psychometrika 56 (1991) 3, pp. 365-379

Persistent link: https://www.econbiz.de/10005757667

Monotone spline transformations for dimension reduction

Winsberg, S.; Ramsay, J. - In: Psychometrika 48 (1983) 4, pp. 575-595

Persistent link: https://www.econbiz.de/10005376329