具共變量測量誤差之右設限數資料已被廣泛的研究，但對現狀或區間設限數據卻很 少研究。研究動機的一部分為斑馬魚之基底細胞癌的研究，其中研究者只知道細胞癌的 發生時間在獻祭時間之前或之後，而共變量Sonic hdgehog 基因表現存有量測誤差。因 此，我們對於具共變量測量誤差之(型I 或型k)區間設限資料，在正比例優劣比模型下， 將提出一個「條件分數法」來分析。條件分數法的重要優勢為不需對真實易有誤差卻未 見之共變量作一分佈假設，因此我們所提估計方法將相較其他處理測量誤差方法更具穩 健性。 Covariate measurement error problems have been extensively studied in the context of right-censored data but less so for current status or interval-censored data. Motivated partly by the zebrafish basal cell carcinoma (BCC) study, where the occurrence time of BCC was only known to lie before or after a sacrifice time and where the covariate (Sonic hedgehog expression) was measured with error, we will propose a conditional score approach to the analysis of (case I / case k) interval-censored data with mismeasured covariates under the proportional odds model. The conditional score approach, originated by Stefanski and Carroll (1987), has the important advantage that it does not need a distributional assumption for unobserved error-prone covariate, rendering the proposed approach more robust and applicable compared to other strategies for handling measurement errors.
