Open AccessBIAS COMPARISON NADARAYA WATSON AND LOCALLY LINEAR KERNEL ESTIMATOR OF NONPARAMETRIC REGRESSION
Author(s) -
Zulfikar Zulfikar
Publication year - 2016
Publication title -
saintekbu
Language(s) - English
Resource type - Journals
eISSN - 2541-1942
pISSN - 1979-7141
DOI - 10.32764/saintekbu.v1i1.31
Subject(s) - mathematics , estimator , statistics , kernel (algebra) , nonparametric statistics , nonparametric regression , kernel regression , mean squared error , linear regression , conditional expectation , combinatorics
dth: 0px; "> Given a data set (xi , yi ) and connecting between xi and yi be assumed to follownonparametric regression model :yi m(xi ) i , i 1,2,...,n.Regresssion curve of m be assumed is an unknown form and i , is an error term in theobservations are IID with mean 0 and finite variance 2.In this paper propose to exist mean conditional estimators with employ the localpolinomial method which polinomial degree p = 0 will be formed the Nadaraya-Watsonestimator and p = 1 to exist the Locally Linear estimator. Furthemore, with the same methodalso be existed the comparison both bias and variance. Kernel estimator will be applied ofthe Canadian Males Data by Murphy and Welch (1990). Key words: Nonparametric estimation, weighted least square, Local polinomial