On the Efficiency of Sensitivity Experiments Analyzed by the Maximum Likelihood Estimation Procedure under the Cumulative Normal Response

摘要

While reviewing some of the implications of a small sample in a sensitivity experiment analyzed by the maximum likelihood estimation procedure under the cumulative normal response, this report provides a measure of efficiency of the experiment as a whole with reference to the estimation of mu and sigma. Such a measure of efficiency provides a perspective for a new look into the existing results as well as a direction for future planning. A design is suggested indicating the levels at which the observations have to be taken to maximize the efficiency of estimation.