D-optimal Exact Design: Weighted Variance Approach and a Continuous Search Technique

Otaru O. Paul *

Department of Mathematics and Statistics, University of Port Harcourt, Nigeria

Enegesele Dennis

Department of Mathematics and Statistics, University of Port Harcourt, Nigeria

*Author to whom correspondence should be addressed.


Abstract

In design of experiment, researchers have formulated various methods for obtaining D-optimal design. The aim of this study therefore is to obtain an N-point exact D-optimal design for a feasibleregion defined on a polynomial model. The weighted variance approach and a continuous search technique were used to obtain a D-optimum measure. The illustrative example buttresses the effectiveness of the method. The minimum variance was obtained in the first iteration and needs no further improvement.

 

Keywords: Weighted variance, D-optimum, gradient vector and variance function


How to Cite

O. Paul, Otaru, and Enegesele Dennis. 2014. “D-Optimal Exact Design: Weighted Variance Approach and a Continuous Search Technique”. Physical Science International Journal 4 (8):1065-72. https://doi.org/10.9734/PSIJ/2014/9141.