Articles |
Semiparametric model-based inference in the presence of missing responses
Academy of Mathematics and Systems Science, Chinese Academy of Science, Beijing 100080, China qhwang{at}amss.ac.cn jackdpj{at}yahoo.com.cn
Received for publication 1 June 2007. Revision received 1 January 2008.
We consider a semiparametric model that parameterizes the conditional density of the response, given covariates, but allows the marginal distribution of the covariates to be completely arbitrary. Responses may be missing. A likelihood-based imputation estimator and a semi-empirical-likelihood-based estimator for the parameter vector describing the conditional density are defined and proved to be asymptotically normal. Semi-empirical loglikelihood functions for the parameter vector and the response mean are derived. It is shown that the two semi-empirical loglikelihood functions are distributed asymptotically as weighted
2 and scaled
2, respectively.
Key Words: Asymptotic efficiency Missing response Multiple imputation Semi-empirical likelihood Auxiliary information Asymptotic Normality
References
-
Cheng P. E. Nonparametric estimation of mean functionals with data missing at random. J. Am. Statist. Assoc (1994) 89:81–7.[CrossRef][Web of Science]
Imbens G. W., Lancaster T. Combining micro and micro data in microeconometric models. Rev. Econ. Stud (1994) 61:655–80.[CrossRef][Web of Science]
Lehmann E. L. Theory of Point Estimation (1983) New York: Wiley.
Owen A. Empirical likelihood ratio confidence intervals for a single functional. Biometrika (1988) 75:237–49.
Owen A. Empirical likelihood ratio confidence regions. Ann. Statist (1990) 18:90–120.[CrossRef]
Qin J. Combining parametric and empirical likelihoods. Biometrika (2000) 87:484–90.
Qin J., Zhang B. Empirical-likelihood-based inference in missing response problems and its application in observational studies. J. R. Statist. Soc. (2007) B 69:101–22.
Rubin D. B. Multiple imputations in sample surveys – a phenomenological Bayesian approach to nonresponse. Proc. Survey Res. Methodes Sect. (1978) Washington, DC: American Statistical Association. 20–34.
Rubin D. B. Multiple Imputation for Nonresponse in Surveys (1987) New York: Wiley.
Rubin D. B., Schenker N. Multiple imputation for interval estimation from simple random samples with ignorable nonresponse. J. Am. Statist. Assoc. (1986) 81:366–77.[CrossRef][Web of Science]
Wang N., Robins J. M. Large-sample theory for parametric multiple imputation procedures. Biometrika (1998) 85:935–48.
Wang Q. H., Rao J. N. K. Empirical likelihood-based inference under imputation for missing response data. Ann. Statist. (2002) 30:896–924.[CrossRef]
Wang Q. H. Likelihood-based imputation inference for mean functionals in the presence of missing responses. Ann. Inst. Statist. Math. (2004) 56:403–14.[CrossRef]
Wang Q. H., Linton O., Härdle W. Semiparametric regression analysis with missing response at random. J. Am. Statist. Assoc. (2004) 99:334–45.[CrossRef][Web of Science]
| ||||||||||||||||||||||||||||||||||||||||||||||||||