删失数据下一类回归模型的参数估计

摘要

For a class of regression model, the least squares estimate and the weighted least squares estimate of parameter are constructed under the random right censorship, the asymptotic normality of the estimators is proved. Simulation results show that the weighted least squares estimate has better properties than the least squares estimate.%考虑一类回归模型,在右删失数据下构造了参数的最小二乘估计和加权最小二乘估计,证明了估计量具有渐近正态性.模拟结果表明加权最小二乘估计比最小二乘估计有优良的性质.