Pre-test estimation and design in the linear model |
| |
| Institution: | 1. Chemistry Department, College of Arts & Science, Wadi Al-dawaser, Prince Sattam Bin Abdulaziz University, Alkharj, Saudi Arabia;2. Chemistry Department, College of Science, Jouf University, Sakaka, Saudi Arabia;3. Department of Chemistry, Faculty of Science, Suez University, Suez, Egypt;4. Department of Chemistry, Faculty of Science, Tanta University, Tanta 31527, Egypt;5. School of Chemical Engineering, Engineering Campus, Universiti Sains Malaysia, 14300 Nibong Tebal, Penang, Malaysia;1. Centre for the Environmental Risk Management of Bushfires, University of Wollongong, NSW 2522, Australia;2. Forest Science Centre, NSW Department of Primary Industries, PO Box 100, Beecroft 2119, Australia;1. School of Natural Sciences, University of Tasmania, Hobart, TAS, Australia;2. CSIRO Environment, Private Bag 44, Winnellie, NT 0821, Australia |
| |
| Abstract: | As a robust method against model deviation we consider a pre-test estimation function. To optimize a continuous design for this problem we give an asymptotic risk matrix for the quadratic loss. The risk will then be given by an isotonic criterion function of the asymptotic risk matrix. As an optimization criterion we look for a design that minimizes the maximal risk in the deviation model under the restriction that the risk in the original model does not exceed a given bound. This optimization problem will be solved for the polynomial regression, the deviation consisting in one additional regression function and the criterion function being the determinant. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
