本篇論文主要是在探討半競爭風險資料下比例風險模型、比例勝算模型和分量迴歸模型的分析。由於非終端事件可能會受到終端事件的相關設限,沒有額外假設下,我們無法對非終端事件做出推論。因此,我們藉由 Archimedean copula 模型來說明非終端事件與終端事件之間的關聯結構。 在 Archimedean copula 模型假設下,對任一模型我們採用平均數插補法與中位數插補法來插補未知的非終端事件時間,並且利用標準方法估計迴歸參數。利用模擬分析來診斷我們所提出的方法之表現。最後,我們運用所提出的方法分析骨髓移植資料。
This thesis focues on the analysis of the proportional hazard model, proportional odds model and quantile regression model under semi-competing risks data. Without extra assumptions, we can not make inference on the non-terminal event because the non-terminal event may be dependently censored by the terminal event. Thus, we use the Archimedean copula model to specify the dependency between the non-terminal event time and the terminal event time. Under the Archimedean copula model assumption, we adopt the mean imputation method and the median imputation method to impute the non-terminal event time and use the standard method to estimate the regression coecients for each model. We examine the nite-sample performance of the proposed approaches by simulation studies. We also apply our suggested approachs to analyze the Bone Marrow Transplant data.