在毒物學的研究中，每日可服劑量 ( Allowable Daily Intakes；簡稱ADI ) 的決定是一項重要的課題。因為每日服用劑量若超過一定的安全劑量，就容易產生毒性反應。本文探討在韋伯分配、對數邏輯斯分配與對數常態分配下的加速失敗時間模型，根據最高可容忍毒性反應所訂定的額外反應估計標竿劑量與標竿劑量下限。模擬研究額外反應、不同存活及設限分布對於標竿劑量估計的影響，最後藉分析一個實驗的資料，說明本文所提方法之應用。 In toxicity study, how to determine the allowable daily intakes(ADI) is an important issue since taking the dose over acceptable region may cause an abnormal adverse. In this study, we estimate the benchmark dose and its lower bound based on the extra response required by the allowable toxic effect when the data are coming from the accelerated failure time model with Weibull, Log-logistic, and Log-normal distribution. The results of a simulation study investigation the effect of extra response and a varity of survival and censoring distributions on the benchmark dose estimation are presented. Finally, we demonstrated the application of the proposed procedure by analyzing an experimental data.
