Abstract
Consider two linear models X i = U′ i β + ε i Y j = V′ j γ + η j with response variables missing at random. In this paper, we assume that X, Y are missing at random (MAR) and use the inverse probability weighted imputation to produce ‘complete’ data sets for X and Y. Based on these data sets, we construct an empirical likelihood (EL) statistic for the difference of X and Y (denoted as Δ), and show that the EL statistic has the limiting distribution of χ 21 , which is used to construct a confidence interval for Δ. Results of a simulation study on the finite sample performance of EL-based confidence intervals on Δ are reported.
Similar content being viewed by others
References
Chen, J., Rao, J.N.K. Asymptotic normality under two-phase sampling designs. Statistica Sinica, 17: 1047–1064 (2007)
Hall, P., La Scala, B. Methodology and algorithms of empirical likelihood. Int. Statist. Rev., 58: 109–127 (1990)
Hall, P., Martin, M. On the bootstrap and two-sample problems. Austral J. Statist, 30A: 179–192 (1988)
Jing, B.Y. Two-sample empirical likelihood method. Statist. Prob. Lett., 24: 315–319 (1995)
Owen, A.B. Empirical likelihood ratio confidence intervals for a single functional. Biometrika, 75: 237–249 (1988)
Owen, A.B. Empirical likelihood ratio confidence regions. Ann. Statist., 18: 90–120 (1990)
Qin, J., Lawless, J. Empirical likelihood and general estimating equations. Ann. Statist., 22: 300–325 (1994)
Qin, Y., Zhang, S. Empirical likelihood confidence intervals for differences between two datasets with missing data. Pattern Recognition Letters, 29: 803–812 (2008)
Qin. Y., Zhao, L. Empirical likelihood ratio intervals for the quantile differences of two populations. Chinese Ann. Math., 18A: 687–694 (1997)
Randles, R.H. On the asymptotic normality of statistics with estimated parameters. Ann. Statist., 10: 462–474 (1982)
Serfling, R.J. Approximation Theorems of Mathematical Statistics. John Wiley & Sons, New York, (1980)
Sun, D. Strong convergence of kernel estimates of regression functions. Chinese Ann. Math., 6A: 480–486 (1985)
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Natural Science Foundation of China (No. 11271088, 11361011, 11201088) and Natural Science Foundation of Guangxi (No. 2013GXNSFAA(019004 and 019007), 2013GXNSFBA019001).
Rights and permissions
About this article
Cite this article
Qin, Ys., Qiu, T. & Lei, Qz. Empirical likelihood for response differences in two linear regression models with missing data. Acta Math. Appl. Sin. Engl. Ser. 31, 963–976 (2015). https://doi.org/10.1007/s10255-015-0516-y
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10255-015-0516-y
Keywords
- linear model
- inverse probability weighted imputation
- empirical likelihood
- missing at random
- confidence interval