Breslow Norman E, Wellner Jon A
Department of Biostatistics, University of Washington.
Scand Stat Theory Appl. 2008 Mar 1;35(1):186-192. doi: 10.1111/j.1467-9469.2007.00574.x.
We state and prove a limit theorem for estimators of a general, possibly infinite dimensional parameter based on unbiased estimating equations containing estimated nuisance parameters. The theorem corrects a gap in the proof of one of the assertions of our paper 'Weighted likelihood for semiparametric models and two-phase stratified samples, with application to Cox regression'.
我们陈述并证明了一个关于基于包含估计干扰参数的无偏估计方程的一般(可能是无限维)参数估计量的极限定理。该定理修正了我们的论文《半参数模型和两阶段分层样本的加权似然性及其在Cox回归中的应用》中一个断言证明中的漏洞。