Summary Five sequential designs for estimating the median in quantal bioassay are compared with a non-sequential one. Mean-square errors of the estimates are calculated exactly in a numerical experiment with the factors: design, first dose, step, number of trials and dose-response curve. Each experimental unit uses 12 animals. Sequential experiments are more accurate, especially for first doses distant from the median. Delayed designs and many trials are best when the median is not well known beforehand. The assumed dose–response curves have little effect on the accuracy of the estimated median.
No takes yet. Share an insight, caveat, or question.
A 1971 study studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: