×

Robust estimation of distribution functions and quantiles with non-ignorable missing data. (English. French summary) Zbl 1281.62108

Summary: This paper considers several robust estimators for distribution functions and quantiles of a response variable when some responses may not be observed under the non-ignorable missing data mechanism. Based on a particular semiparametric regression model for non-ignorable missing response, we propose a nonparametric/semiparametric estimation method and an augmented inverse probability weighted imputation method to estimate the distribution function and quantiles of a response variable. Under some regularity conditions, we derive asymptotic properties of the proposed distribution function and quantile estimators.
Two empirical log-likelihood functions are also defined to construct confidence intervals for the distribution function of a response variable. Simulation studies show that our proposed methods are robust. In particular, the semiparametric estimator is more efficient than the nonparametric estimator, and the inverse probability weighted imputation estimator is bias-corrected.

MSC:

62G08 Nonparametric regression and quantile regression
62G35 Nonparametric robustness
62G07 Density estimation
62G20 Asymptotic properties of nonparametric inference
62G05 Nonparametric estimation
62F10 Point estimation
65C60 Computational problems in statistics (MSC2010)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chambers, Estimating distribution function from survey data, Biometrika pp 597– (1986) · Zbl 0614.62005 · doi:10.1093/biomet/73.3.597
[2] Chen, A pseudo empirical likelihood approach to the effective use of auxiliary inforamtion in complex survey, Statistica Sinica pp 385– (1999)
[3] Chen, Estimation of distribution function and quantiles using the model-calibrated pseudo empirical likelihood method, Statistica Sinica pp 1223– (2002) · Zbl 1004.62008
[4] Cheng, Kernel estimation of distribution functions and quantiles with missing data, Statistica Sinica pp 63– (1996) · Zbl 0839.62038
[5] Groeneboom , P. Wellner , J. A. 1992
[6] Heckman, The common structure of statistical models of truncation, sample selection and limited dependent variables and a simple estimator for such models, Annals of Economic and Social Measurement pp 475– (1976)
[7] Horvitz, A generalization of sampling without replacement from a finite universe, Journal of the American Statistical Association pp 663– (1952) · Zbl 0047.38301 · doi:10.1080/01621459.1952.10483446
[8] Hu, Dimension reducted kernel estimation for distribution function with incomplete data, Journal of Statistical Planning and Inference pp 3084– (2011) · Zbl 1216.62058 · doi:10.1016/j.jspi.2011.03.030
[9] Ibrahim, Missing responses in generalised linear mixed models when the missing data mechanism is nonignorbale, Biometrika pp 551– (2001) · Zbl 0984.62047 · doi:10.1093/biomet/88.2.551
[10] Kaplan, Nonparametric estimation from incomplete observations, Journal of the American Statistical Association pp 457– (1958) · Zbl 0089.14801 · doi:10.1080/01621459.1958.10501452
[11] Kim, A semiparametric estimation of mean functionals with nonignorable missing data, Journal of the American Statistical Association pp 157– (2011) · Zbl 1396.62032 · doi:10.1198/jasa.2011.tm10104
[12] Liu, Distribution estimation with auxiliary informaiton for missing data, Journal of Statistical Planning and Inference pp 711– (2011) · Zbl 1214.62040 · doi:10.1016/j.jspi.2010.07.015
[13] Little , R. J. A. Rubin , D. B. 2002
[14] Nadaraya, Some new estimates for distribution functions, Theory of Probability and Its Applications pp 497– (1964a) · Zbl 0152.17605 · doi:10.1137/1109069
[15] Nadaraya, On estimating regression, Theory of Probability and Its Applications pp 141– (1964b) · doi:10.1137/1109020
[16] Owen, Empirical likelihood ratio confidence intervals, Biometrika pp 237– (1988) · Zbl 0641.62032 · doi:10.1093/biomet/75.2.237
[17] Owen, Empirical likelihood confidence regions, The Annals of Statistics pp 90– (1990) · Zbl 0712.62040 · doi:10.1214/aos/1176347494
[18] Randles, On the asymptotic normality of statistics with estimated parameters, The Annals of Statistics pp 462– (1982) · Zbl 0493.62022 · doi:10.1214/aos/1176345787
[19] Rao, On estimating distribution function and quantiles from survey data using auxiliary information, Biometrika pp 365– (1990) · Zbl 0716.62013 · doi:10.1093/biomet/77.2.365
[20] Reiss, Nonparametric estimation of smooth distribution functions, Scandinavian Journal of Statistics pp 116– (1981) · Zbl 0468.62034
[21] Robins, Estimation of regression coefficients when some regressors are not always observed, Journal of the American Statistical Association pp 846– (1994) · Zbl 0815.62043 · doi:10.1080/01621459.1994.10476818
[22] Rosenbaum, Constructing a control group using multivariate matched sampling methods that incorporate the propensity score, The American Statistician pp 33– (1985)
[23] Wang, Empirical likelihood confidence bands for distribution functions with missing responses, Journal of Statistical Planning and Inference pp 2778– (2010) · Zbl 1188.62148 · doi:10.1016/j.jspi.2010.03.044
[24] Wang, Empirical likelihood-based inference under imputation for missing response data, The Annals of Statistics pp 896– (2002)
[25] Watson, Smooth regression analysis, Sankhya Series A pp 359– (1964) · Zbl 0137.13002
[26] Wu, A model-calibration approach to using complete auxiliary information from survey data, Journal of the American Statistical Association pp 185– (2001) · Zbl 1015.62005 · doi:10.1198/016214501750333054
[27] Xue, Empirical likelihood confidence intervals for response mean with data missing at random, Scandinavian Journal of Statistics pp 671– (2009a) · Zbl 1223.62055 · doi:10.1111/j.1467-9469.2009.00651.x
[28] Xue, Empirical likelihood for linear models with missing reponses, Journal of Multivariate Analysis pp 1353– (2009b) · Zbl 1162.62038 · doi:10.1016/j.jmva.2008.12.009
[29] Xue, Empirical likelihood for semiparametric regression models with missing reponses, Journal of Multivariate Analysis pp 723– (2011) · Zbl 1327.62231 · doi:10.1016/j.jmva.2010.11.001
[30] Zhao, Regression analysis with missing covariate data using estimating equations, Biometrics pp 1165– (1996) · Zbl 0925.62304 · doi:10.2307/2532833
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.