陳秀熙Tai, Jen;Chen, Hsiu-Hsi臺灣大學:流行病學研究所何慶勳Ho, Ching-HsunChing-HsunHo2010-05-052018-06-292010-05-052018-06-292009U0001-0608200914012400http://ntur.lib.ntu.edu.tw//handle/246246/180776於篩檢欲檢驗出某種疾病時，當採用兩種檢驗工具而確診動作僅施予初步診斷結果為陽性的個案，則無法求得此二工具之敏感度與特異度。先前的研究藉由假設檢驗工具間為獨立或是其相依性為同質下，利用最大概似函數法或是捉捕-再捉捕法求出個別之準確度估計。由於有關工具間的相依性假設往往存在許多爭議，因此本研究利用兩種相依模式去討論異質相依性所造成的影響，研究結果顯示相依性的方向並不會干擾準確度之估計，但其強弱卻會產生相當大的影響。When diagnosing a disease in a screening program, two diagnostic tests may be applied simultaneously. To confirm the accuracy of the two tests, a third gold standard test will usually be also used. However, due to realistic reasons, the confirmatory procedure is limited to individuals with positive results. Previous approaches assumed independence or homogeneous dependence of the two tests and used maximum likelihood or capture-recapture method to estimate the accuracy for each test. However, there are controversies about the dependence assumptions. Therefore, in this thesis we adopted two dependent models for discussing the influence of heterogeneous dependence on diagnostic accuracy. The results indicate that the direction of dependence will not affect accuracy estimates, but the strength will.第一章 緒論 ............................................1.1 評估檢驗工具的指標...................................2.2 多個檢驗工具的合併...................................2.3 研究動機.............................................3.4 研究目的.............................................4二章 文獻回顧..........................................5.1 資料結構與符號定義...................................5.2 極端驗證偏差的處理...................................8.3 latent class analysis（LCA）method .................11.4 兩工具間的條件相依性................................12三章 研究方法.........................................14.1 Walter, Merwe and Maritz的模式......................14.2 相依參數模式........................................17.3 實證資料研究........................................21四章 模擬研究.........................................27.1模擬步驟與設定........................................27.2模擬結果..............................................28五章 討論與建議.......................................35考文獻.......................................................37錄錄A 半潛藏資料造成無法直接得到各參數估計之說明.........42錄B 參數估計方法-以model1_1為例........................43錄C 四個組合於異質相依性下的各參數估計值...............46錄D 模擬結果...........................................62application/pdf1520360 bytesapplication/pdfen-US準確度相依性檢驗工具accuracydependencediagnostic testthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/180776/1/ntu-98-R96842023-1.pdf