长度偏差右删失数据剩余寿命的分位数回归

本文研究长度偏差数据下剩余寿命分位数模型的估计方法,充分考虑有偏抽样机制对模型估计的影响.如果忽略这种有偏性会导致估计产生严重偏差甚至错误的结果.本文首先针对长度偏差右删失数据的剩余寿命分位数提出了对数形式的线性回归模型,对删失变量与协变量独立和不独立的两种情况利用估计方程给出了模型参数的估计.其次,通过经验过程和弱收敛理论给出了参数估计的相合性和渐近正态性.最后,本文对提出的估计方法进行了数值模拟并用该方法对奥斯卡奖数据进行分析.

Quantile Residual Regression with Length-Biased and Right-Censored Data

We use the quantile residual lifetime models to analyze the length-biased data that are often encountered in observational studies. Ignoring sampling bias may lead to substantial estimation bias and fallacious inference. We consider a conditional log-linear regression model on the residual lifetimes at a fixed time point under right-censored and length-biased data for both covariate-independent censoring and covariate-dependent censoring. Consistency and asymptotically normalities of the regression estimators are established. Simmulation studies are performed to assess finite sample properties of the regression parameter estimator. Finally, we analyze the Oscar real data by the proposed method.