| dc.contributor.advisor | 陸行 | zh_TW |
| dc.contributor.advisor | Luh, Hsing | en_US |
| dc.contributor.author (Authors) | 林亞萱 | zh_TW |
| dc.contributor.author (Authors) | Lin, Ya-Syuan | en_US |
| dc.creator (作者) | 林亞萱 | zh_TW |
| dc.creator (作者) | Lin, Ya-Syuan | en_US |
| dc.date (日期) | 2022 | en_US |
| dc.date.accessioned | 2-May-2022 15:02:34 (UTC+8) | - |
| dc.date.available | 2-May-2022 15:02:34 (UTC+8) | - |
| dc.date.issued (上傳時間) | 2-May-2022 15:02:34 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0107751011 | en_US |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/139991 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 應用數學系 | zh_TW |
| dc.description (描述) | 107751011 | zh_TW |
| dc.description.abstract (摘要) | 本研究以部分設限資料之類馬可夫模型為基礎，並根據健保資料庫蒐集之數據直接驗證此模型之可行性。根據研究顯示，類馬可夫模型可以在醫學研究中分析患者狀態轉移的過程，且醫學研究中時常存在病程不完整的情況，所以我們認為部分設限資料之類馬可夫模型非常適合被應用在醫學研究中。希望透過現有的健保資料庫數據，將模型與實際數據作結合，活化醫療數據和使用。驗證結果顯示，此估計模型在資料完整情況下是相當好的估計方法; 而在設限情況下透過模型估計出來的轉移機率與實際轉移機率無太大差異，所以此估計模型確實可以用來估計我們所感興趣的轉移機率。並且，雖然資料完整未必在所有疾病都可準確估計，但可以看出整體趨勢往實際數值靠近。 | zh_TW |
| dc.description.abstract (摘要) | This thesis is based on the semi-Markov models for partially censored data. Data from the National Health Insurance Research Database are used to evaluate the feasibility of the model.According to the research, semi-Markov models can be used to analyze the process of state transitions of the patient. However, the patient history in medical research is sometimes incomplete. We evaluate the semi-Markov models for partially censored data and find it can greatly fit for medical research. Patient data is extracted from National Health Insurance Research Database, enhancing the sustainability of medical data and application.The verification result shows that this model performs well when the data is complete. Meanwhile, the estimate of transition probability under the censored situation is nonsignificantly different compared to the case with complete information. We can conclude that this model is suitable to estimate the transition probability that we are interested in. Still, although the completeness of information may not always induce precise prediction of all risks, but the approximation by the model correctly reflects the trend. | en_US |
| dc.description.tableofcontents | 中文摘要............................................... iAbstract..............................................ii目錄................................................. iii表目錄................................................ v圖目錄................................................ vi第一章 緒論............................................ 1第一節 研究背景........................................ 1第二節 研究動機........................................ 1第三節 研究架構.........................................1第二章 文獻探討........................................ 3第一節 馬可夫模型文獻探討............................... 3第二節 馬可夫模型與類馬可夫模型之差異.................... 3第三節 部分設限資料之類馬可夫模型........................ 4第三章 部分設限資料之類馬可夫模型....................... 5第一節 模型定義........................................ 5第二節 無母數最大概似估計法............................. 6第三節 θˆ(i, j) 與 Qˆ(vk; i, j) 之變異數............... 8第四章 研究與實踐..................................... 10第一節 資料來源....................................... 10第二節 數據整理....................................... 11第三節 核對理論和數據................................. 12一、pijk、pˆijk...................................... 12二、θ(i, j; vk) 、θˆ(i, j, vk)....................... 12三、θ(i, j) 、θˆ(i, j) .............................. 12四、Q(t; i, j)、Qˆ(t; i, j).......................... 12五、var{θˆ(i, j)}、var{Qˆ(vk; i, j)}................ 12第四節 設限情況下之數據比較............................ 13第五章 研究結論與建議................................. 16第一節 研究結論....................................... 16第二節 未來研究方向................................... 17參考文獻............................................. 18附錄 A 相關名詞定義................................... 20A.1 類馬可夫模型定義.................................. 20A.2 設限觀察值的馬可夫更新過程之定義................... 20附錄 B 數據整理表格................................... 21 | zh_TW |
| dc.format.extent | 16450395 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0107751011 | en_US |
| dc.subject (關鍵詞) | 類馬可夫模型 | zh_TW |
| dc.subject (關鍵詞) | 設限資料 | zh_TW |
| dc.subject (關鍵詞) | 評估風險 | zh_TW |
| dc.subject (關鍵詞) | Semi-Markov | en_US |
| dc.subject (關鍵詞) | Censored data | en_US |
| dc.subject (關鍵詞) | Risk accessment | en_US |
| dc.title (題名) | 以類馬可夫模式評估疾病風險 | zh_TW |
| dc.title (題名) | Evaluate Prognostic Risks by Semi-Markov Model | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | [1] G. H. Weiss and M. Zelen. A semi-markov model for clinical trials. Journal of AppliedProbability, 2(2):269–285, 1965.[2] B. W. Turnbull, B. W. Brown Jr, and M. Hu. Survivorship analysis of heart transplant data.Journal of the American Statistical Association, 69(345):74–80, 1974.[3] S. W. Lagakos. A stochastic model for censored-survival data in the presence of anauxiliary variable. Biometrics, pages 551–559, 1976.[4] S. W. Lagakos, C. J. Sommer, and M. Zelen. Semi-markov models for partially censoreddata. Biometrika, 65(2):311–317, 1978.[5] James R Broyles, Jeffery K Cochran, and Douglas C Montgomery. A statistical markovchain approximation of transient hospital inpatient inventory. European Journal ofOperational Research, 207(3):1645–1657, 2010.[6] Gordon J Taylor, Sally I McClean, and Peter H Millard. Using a continuous-time markovmodel with poisson arrivals to describe the movements of geriatric patients. Appliedstochastic models and data analysis, 14(2):165–174, 1998.[7] Chiying Wang, Sergio A Alvarez, Carolina Ruiz, and Majaz Moonis. Computationalmodeling of sleep stage dynamics using weibull semi-markov chains. In HEALTHINF,pages 122–130, 2013.[8] Benoit Liquet, Jean-François Timsit, and Virginie Rondeau. Investigating hospitalheterogeneity with a multi-state frailty model: application to nosocomial pneumoniadisease in intensive care units. BMC medical research methodology, 12(1):1–14, 2012.18[9] Jean-François Coeurjolly, Moliere Nguile-Makao, Jean-François Timsit, and BenoitLiquet. Attributable risk estimation for adjusted disability multistate models: applicationto nosocomial infections. Biometrical journal, 54(5):600–616, 2012.[10] C. C. Huang. Nonhomogeneous Markov Chains and Their Applications. Ph. D. thesis,Iowa State University, 1977.[11] A. Listwon and P. Saint-Pierre. Semimarkov: An R package for parametric estimation inmulti-state semi-markov models. Journal of Statistical Software, 66(6):784, 2015.[12] A. Asanjarani, B. Liquet, and Y. Nazarathy. Estimation of semi-markov multi-state models:a comparison of the sojourn times and transition intensities approaches. The InternationalJournal of Biostatistics, 2021. doi.org/10.1515/ijb-2020-0083[13] J. E. Ruiz-Castro and R. Pérez-Ocón. A semi-markov model in biomedical studies. 2004.[14] M. J. Phelan. Estimating the transition probabilities from censored markov renewalprocesses. Statistics & probability letters, 10(1):43–47, 1990.[15] E. L. Kaplan and P. Meier. Nonparametric estimation from incomplete observations.Journal of the American statistical association, 53(282):457–481, 1958. | zh_TW |
| dc.identifier.doi (DOI) | 10.6814/NCCU202200399 | en_US |
