Research On Longitudinal Data Modeling Problem Under Mixed Missingness

We mainly focus on estimations in a longitudinal study with nonignorable inter-mittent nonresponse and dropout.To handle the identifiability issue,we take a time-independent covariate as nonresponse instrument which is independent of nonresponse propensity conditioned on other covariates and responses to ensure the identifiability of nonresponse propensity.The nonresponse propensity is assumed to be a parametric model,and the corresponding parameters are estimated by using the generalized method of moments approach.Then the marginal response means are estimated by inverse probability weighting method.Furthermore,to improve the robustness and efficiency of estimators,we derive an augmented inverse probability weighting estimator.Both inverse probability weighting estimator and augmented inverse probability weighting estimator are consistent and asymptotically normally distributed when the nonresponse propensity is correctly specified.Simulation studies and a real data analysis show that the proposed approach can yields highly efficient estimators under some conditions.