Efficient restricted estimators for conditional mean models with missing data
Author:
- 26 August 2011
- journal article
- research article
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 98 (3) , 663-684
Abstract
Consider a conditional mean model with missing data on the response or explanatory variables due to two-phase sampling or nonresponse. Robins et al. (1994) introduced a class of augmented inverse-probability-weighted estimators, depending on a vector of functions of explanatory variables and a vector of functions of coarsened data. Tsiatis (2006) studied two classes of restricted estimators, class 1 with both vectors restricted to finite-dimensional linear subspaces and class 2 with the first vector of functions restricted to a finite-dimensional linear subspace. We introduce a third class of restricted estimators, class 3, with the second vector of functions restricted to a finite-dimensional subspace. We derive a new estimator, which is asymptotically optimal in class 1, by the methods of nonparametric and empirical likelihood. We propose a hybrid strategy to obtain estimators that are asymptotically optimal in class 1 and locally optimal in class 2 or class 3. The advantages of the hybrid, likelihood estimator based on classes 1 and 3 are shown in a simulation study and a real-data example.Keywords
This publication has 17 references indexed in Scilit:
- Improving Semiparametric Estimation by Using Surrogate DataJournal of the Royal Statistical Society Series B: Statistical Methodology, 2008
- Semiparametric efficient estimation for the auxiliary outcome problem with the conditional mean modelCanadian Journal of Statistics, 2004
- Higher Order Properties of Gmm and Generalized Empirical Likelihood EstimatorsEconometrica, 2004
- Large sample theory for semiparametric regression models with two-phase, outcome dependent samplingThe Annals of Statistics, 2003
- A Pseudoscore Estimator for Regression Problems With Two-Phase SamplingJournal of the American Statistical Association, 2003
- Semiparametric Methods for Response-Selective and Missing Data Problems in RegressionJournal of the Royal Statistical Society Series B: Statistical Methodology, 1999
- Estimation of Regression Coefficients When Some Regressors Are Not Always ObservedJournal of the American Statistical Association, 1994
- Empirical Likelihood and General Estimating EquationsThe Annals of Statistics, 1994
- Large Sample Properties of Generalized Method of Moments EstimatorsEconometrica, 1982
- The Estimation of Choice Probabilities from Choice Based SamplesEconometrica, 1977