A Missing Information Principle and $M$-Estimators in Regression Analysis with Censored and Truncated Data
Lai, Tze Leung ; Ying, Zhiliang
Ann. Statist., Tome 22 (1994) no. 1, p. 1222-1255 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
A general missing information principle is proposed for constructing $M$-estimators of regression parameters in the presence of left truncation and right censoring on the observed responses. By making use of martingale central limit theorems and empirical process theory, the asymptotic normality of $M$-estimators is established under certain assumptions. Asymptotically efficient $M$-estimators are also developed by using data-dependent score functions. In addition, robustness properties of the estimators are discussed and formulas for their influence functions are derived for the robustness analysis.
Publié le : 1994-09-14
Classification:  $M$-estimator,  censoring,  truncation,  self-consistency,  linear regression,  martingale,  asymptotic normality,  influence function,  robustness,  62J99,  60F05,  62E20,  62G05,  62G35 
@article{1176325627,
     author = {Lai, Tze Leung and Ying, Zhiliang},
     title = {A Missing Information Principle and $M$-Estimators in Regression Analysis with Censored and Truncated Data},
     journal = {Ann. Statist.},
     volume = {22},
     number = {1},
     year = {1994},
     pages = { 1222-1255},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176325627}
}

Lai, Tze Leung; Ying, Zhiliang. A Missing Information Principle and $M$-Estimators in Regression Analysis with Censored and Truncated Data. Ann. Statist., Tome 22 (1994) no. 1, pp.  1222-1255. http://gdmltest.u-ga.fr/item/1176325627/