Bounded-Influence Regression Estimation for Mixture Experiments

Authors : Orkun Coşkuntuncel

Pages : 1020-1037

Doi:10.17860/mersinefd.443584

View : 14 | Download : 14

Publication Date : 2018-12-25

Article Type : Research

Abstract :Ordinary Least Squares (OLS) estimator is widely used technique for estimating the regression coefficient in mixture experiments. But this estimator is very sensitive to outliers and/or multicollinearity problems. The aim of this paper is to propose estimators for the regression parameters of a mixture model that can combat with the above problems. For this purpose, Generalized M (GM) estimation, which is more resistant to outliers in the y and / or x directions and regression estimators such as ridge and Liu, which is effective against the multicollinearity, were used together. The Mean Square Error (MSE) properties of proposed estimator has been examined and shown to be smaller than biased and GM estimates. Also performance of the combined estimator is illustrated by examples.
Keywords : Regression, Ridge regression, Liu estimator, Robustness, GM estimator