DOI: 10.21276/sjpms

Pages: 102-108

Consider two linear models with missing data, where the covariates are not missing and response variables are missing at random (MAR). The inverse probability weighted imputation is used to impute the missing data of response variables. We construct the empirical log-likelihood ratios on mean differences of two response variables. And the asymptotic distributions for the empirical log-likelihood ratios of mean differences of response variables are standard 2  1 comparing with the results of previous studies. The empirical likelihood confidence intervals for mean differences of response variables is more accurate because the errors caused right of the coefficient estimates is reduced. Keywords: missing data; inverse probability weighted imputation; mean; empirical likelihood; confidence intervals