Approximate methods using ranks for regression with censored data
删失数据回归的近似秩方法
SUMMARY An approximation to marginal rank likelihoods is given and used to make inferences for the linear regression model with censored data. The approximations involve linear rank statistics, adapted for censored data, and estimates of their variance. Various explicit scores are given for right censored data and logistic scores for doubly censored data. Inferences using the approximate rank analysis are compared with inferences using fully and partially parametric…