Likelihood-Based Experimental Design for Estimation of Ed 50
Article first published online: 25 MAY 2004
Volume 55, Issue 4, pages 1030–1037, December 1999
How to Cite
Minkin, S. and Kundhal, K. (1999), Likelihood-Based Experimental Design for Estimation of Ed 50. Biometrics, 55: 1030–1037. doi: 10.1111/j.0006-341X.1999.01030.x
- Issue published online: 25 MAY 2004
- Article first published online: 25 MAY 2004
- Received December 1997. Revised October 1998. Accepted December 1998.
- Median lethal dose;
- Minimax designs;
- Optimal designs;
- Radiation therapy
Summary. In selecting the best dosage choice for the estimation of ED 50, it is natural to try to minimize the length of the confidence intervals. In this presentation, the dose allocation that minimizes the length of the likelihood-based confidence intervals is presented and compared with alternative allocations that have been proposed based on the length of different types of confidence intervals, such as those based on the asymptotic variance or on Fieller's Theorem. Effective strategies to deal with the parameter dependence of these allocations are explored. A series of experiments to evaluate the effect of small doses per fraction on the radiation tolerance of the rat cervical spinal cord provide the motivation and an illustration for the proposed procedures.