Adji Achmad Rinaldo Fernandes, I Nyoman Budiantara, Bambang Widjanarko Otok
Reproducing Kernel Hilbert Space (RKHS) play a central role to solve the Penalized Weighted Least Square (PWLS) in Spline Estimator of nonparametric regression analysis. The purposes of this research is to obtain the RKHS approach in PWLS to solve the estimator of regression curve. Base of RKHS, the curve nonparametric regression form is f (x) = Td + Vc. Solving the weighted of PLWS coming from variance-covariance Ŵ is equals to solving the Σ11.1,Σ11.2,..Σ22.r,...Σ12.11,...Σ12.rr.For the purposes of f estimation, RKHS approach with completes the PWLS criterion is fα= A*(λ)y, with A(λ)=T(T′M-1ŴT)-1 T′M-1Ŵ + VM-1ŴI-T(T′M-1ŴT)-1 T′M-1Ŵ] © 2014 Adji Achmad Rinaldo Fernandes, I Nyoman Budiantara, Bambang Widjanarko Otok and Suhartono. © 2014 Adji Achmad Rinaldo Fernandes.
Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Brawijaya, Jalan Veteran Malang, Indonesia; Department of Statistics, Faculty of Mathematics and Natural Sciences, Sepuluh Nopember Institute of Technology, Jalan Arif Rahman Hakim Surabaya, Indonesia
